no code implementations • CVPR 2013 • Ke Chen, Shaogang Gong, Tao Xiang, Chen Change Loy
A number of computer vision problems such as human age estimation, crowd density estimation and body/face pose (view angle) estimation can be formulated as a regression problem by learning a mapping function between a high dimensional vector-formed feature input and a scalarvalued output.
no code implementations • CVPR 2014 • Jing Shao, Chen Change Loy, Xiaogang Wang
Groups are the primary entities that make up a crowd.
no code implementations • CVPR 2014 • Xiatian Zhu, Chen Change Loy, Shaogang Gong
Spectral clustering requires robust and meaningful affinity graphs as input in order to form clusters with desired structures that can well support human intuition.
no code implementations • 18 Aug 2014 • Zhanpeng Zhang, Ping Luo, Chen Change Loy, Xiaoou Tang
In this study, we show that landmark detection or face alignment task is not a single and independent problem.
Ranked #13 on Unsupervised Facial Landmark Detection on MAFL
no code implementations • 2 Sep 2014 • Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang
We show extensive results on combining various popular databases (LFW, AFLW, LFPW, HELEN) for improved cross-dataset and unseen data alignment.
no code implementations • 14 Oct 2014 • Mei Kuan Lim, Ven Jyn Kok, Chen Change Loy, Chee Seng Chan
This paper proposes a novel framework to identify and localize salient regions in a crowd scene, by transforming low-level features extracted from crowd motion field into a global similarity structure.
60 code implementations • 31 Dec 2014 • Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang
We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
Ranked #2 on Video Super-Resolution on Xiph HD - 4x upscaling
no code implementations • 5 Jan 2015 • Yubin Deng, Ping Luo, Chen Change Loy, Xiaoou Tang
Learning to recognize pedestrian attributes at far distance is a challenging problem in visual surveillance since face and body close-shots are hardly available; instead, only far-view image frames of pedestrian are given.
no code implementations • 13 Jan 2015 • Xiatian Zhu, Chen Change Loy, Shaogang Gong
Many visual surveillance tasks, e. g. video summarisation, is conventionally accomplished through analysing imagerybased features.
4 code implementations • ICCV 2015 • Chao Dong, Yubin Deng, Chen Change Loy, Xiaoou Tang
Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring.
no code implementations • CVPR 2015 • Jing Shao, Kai Kang, Chen Change Loy, Xiaogang Wang
We further measure user study performance on WWW and compare this with the proposed deep models.
no code implementations • 7 Jun 2015 • Chao Dong, Ximei Zhu, Yubin Deng, Chen Change Loy, Yu Qiao
Text image super-resolution is a challenging yet open research problem in the computer vision community.
1 code implementation • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015 • Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang
We present a novel face alignment framework based on coarse-to-fine shape searching.
Ranked #20 on Face Alignment on AFLW-19
1 code implementation • 14 Jun 2015 • Pan He, Weilin Huang, Yu Qiao, Chen Change Loy, Xiaoou Tang
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem.
3 code implementations • CVPR 2015 • Linjie Yang, Ping Luo, Chen Change Loy, Xiaoou Tang
Updated on 24/09/2015: This update provides preliminary experiment results for fine-grained classification on the surveillance data of CompCars.
Ranked #5 on Fine-Grained Image Classification on CompCars
no code implementations • ICCV 2015 • Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts.
Ranked #89 on Semantic Segmentation on Cityscapes test
no code implementations • ICCV 2015 • Zhanpeng Zhang, Ping Luo, Chen Change Loy, Xiaoou Tang
Social relation defines the association, e. g, warm, friendliness, and dominance, between two or more people.
1 code implementation • ICCV 2015 • Shuo Yang, Ping Luo, Chen Change Loy, Xiaoou Tang
In this paper, we propose a novel deep convolutional network (DCN) that achieves outstanding performance on FDDB, PASCAL Face, and AFW.
no code implementations • 16 Nov 2015 • Heng Yang, Xuhui Jia, Chen Change Loy, Peter Robinson
In this paper, we carry out a rigorous evaluation of these methods by making the following contributions: 1) we proposes a new evaluation metric for face alignment on a set of images, i. e., area under error distribution curve within a threshold, AUC$_\alpha$, given the fact that the traditional evaluation measure (mean error) is very sensitive to big alignment error.
no code implementations • 20 Nov 2015 • Shizhan Zhu, Cheng Li, Chen Change Loy, Xiaoou Tang
The unified framework seamlessly handles different viewpoints and landmark protocols, and it is trained by optimising directly on landmark locations, thus yielding superior results on arbitrary-view face alignment.
1 code implementation • CVPR 2016 • Shuo Yang, Ping Luo, Chen Change Loy, Xiaoou Tang
Face detection is one of the most studied topics in the computer vision community.
Ranked #34 on Face Detection on WIDER Face (Medium)
no code implementations • 3 Feb 2016 • Chen Huang, Chen Change Loy, Xiaoou Tang
These methods further deteriorate on small, imbalanced data that has a large degree of class overlap.
no code implementations • CVPR 2016 • Chen Huang, Chen Change Loy, Xiaoou Tang
Attributes offer useful mid-level features to interpret visual data.
no code implementations • CVPR 2016 • Chen Huang, Yining Li, Chen Change Loy, Xiaoou Tang
We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain both inter-cluster and inter-class margins.
no code implementations • 23 Jun 2016 • Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang
Semantic segmentation tasks can be well modeled by Markov Random Field (MRF).
no code implementations • 18 Jul 2016 • Shizhan Zhu, Sifei Liu, Chen Change Loy, Xiaoou Tang
We present a novel framework for hallucinating faces of unconstrained poses and with very low resolution (face size as small as 5pxIOD).
Ranked #5 on Image Super-Resolution on VggFace2 - 8x upscaling
14 code implementations • 1 Aug 2016 • Chao Dong, Chen Change Loy, Xiaoou Tang
As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality.
2 code implementations • 9 Aug 2016 • Ke Yu, Chao Dong, Chen Change Loy, Xiaoou Tang
Lossy compression introduces complex compression artifacts, particularly blocking artifacts, ringing effects and blurring.
no code implementations • 21 Sep 2016 • Zhanpeng Zhang, Ping Luo, Chen Change Loy, Xiaoou Tang
Unlike existing models that typically learn from facial expression labels alone, we devise an effective multitask network that is capable of learning from rich auxiliary attributes such as gender, age, and head pose, beyond just facial expression data.
1 code implementation • 4 Oct 2016 • Yubin Deng, Chen Change Loy, Xiaoou Tang
This survey aims at reviewing recent computer vision techniques used in the assessment of image aesthetic quality.
no code implementations • NeurIPS 2016 • Chen Huang, Chen Change Loy, Xiaoou Tang
Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric.
Ranked #27 on Metric Learning on CUB-200-2011
3 code implementations • CVPR 2017 • Xingcheng Zhang, Zhizhong Li, Chen Change Loy, Dahua Lin
A number of studies have shown that increasing the depth or width of convolutional networks is a rewarding approach to improve the performance of image recognition.
no code implementations • 29 Jan 2017 • Shuo Yang, Ping Luo, Chen Change Loy, Xiaoou Tang
We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision.
1 code implementation • CVPR 2017 • Xiaoxiao Li, Ziwei Liu, Ping Luo, Chen Change Loy, Xiaoou Tang
Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models.
Ranked #22 on Semantic Segmentation on PASCAL VOC 2012 test
1 code implementation • 21 Apr 2017 • Zhibo Yang, Huanle Xu, Jianyuan Deng, Chen Change Loy, Wing Cheong Lau
Particularly, we further discover a new type of chromatic distortion in high-density color QR codes, cross-module color interference, caused by the high density which also makes the geometric distortion correction more challenging.
no code implementations • 9 Jun 2017 • Shuo Yang, Yuanjun Xiong, Chen Change Loy, Xiaoou Tang
Specifically, our method achieves 76. 4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.
1 code implementation • 13 Jul 2017 • Yue He, Kaidi Cao, Cheng Li, Chen Change Loy
Given a large number of unlabeled face images, face grouping aims at clustering the images into individual identities present in the data.
1 code implementation • 17 Jul 2017 • Yubin Deng, Chen Change Loy, Xiaoou Tang
We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement.
1 code implementation • CVPR 2017 • Kai Chen, Hang Song, Chen Change Loy, Dahua Lin
Despite the remarkable progress in recent years, detecting objects in a new context remains a challenging task.
3 code implementations • 1 Aug 2017 • Xiaoxiao Li, Yuankai Qi, Zhe Wang, Kai Chen, Ziwei Liu, Jianping Shi, Ping Luo, Xiaoou Tang, Chen Change Loy
Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
1 code implementation • 31 Aug 2017 • Yunxuan Zhang, Li Liu, Cheng Li, Chen Change Loy
We introduce a novel approach for annotating large quantity of in-the-wild facial images with high-quality posterior age distribution as labels.
Ranked #7 on Age Estimation on MORPH Album2 (using extra training data)
no code implementations • ICCV 2017 • Shizhan Zhu, Sanja Fidler, Raquel Urtasun, Dahua Lin, Chen Change Loy
In the second stage, a generative model with a newly proposed compositional mapping layer is used to render the final image with precise regions and textures conditioned on this map.
no code implementations • 2 Dec 2017 • Xiaohang Zhan, Ziwei Liu, Ping Luo, Xiaoou Tang, Chen Change Loy
The key of this new form of learning is to design a proxy task (e. g. image colorization), from which a discriminative loss can be formulated on unlabeled data.
1 code implementation • CVPR 2018 • Kaidi Cao, Yu Rong, Cheng Li, Xiaoou Tang, Chen Change Loy
However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces.
Ranked #1 on Face Identification on IJB-A
no code implementations • ECCV 2018 • Xiaoxiao Li, Chen Change Loy
The problem of video object segmentation can become extremely challenging when multiple instances co-exist.
4 code implementations • CVPR 2018 • Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
In this paper, we show that it is possible to recover textures faithful to semantic classes.
Ranked #55 on Image Super-Resolution on BSD100 - 4x upscaling
2 code implementations • CVPR 2018 • Ke Yu, Chao Dong, Liang Lin, Chen Change Loy
We investigate a novel approach for image restoration by reinforcement learning.
1 code implementation • CVPR 2018 • Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, Dahua Lin
High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e. g. those that require detecting objects from video streams in real time.
4 code implementations • CVPR 2018 • Tak-Wai Hui, Xiaoou Tang, Chen Change Loy
FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation.
Ranked #10 on Optical Flow Estimation on KITTI 2012
1 code implementation • 1 Jun 2018 • Chen Huang, Yining Li, Chen Change Loy, Xiaoou Tang
Data for face analysis often exhibit highly-skewed class distribution, i. e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances.
1 code implementation • NeurIPS 2018 • Ding Liu, Bihan Wen, Yuchen Fan, Chen Change Loy, Thomas S. Huang
The main contributions of this work are: (1) Unlike existing methods that measure self-similarity in an isolated manner, the proposed non-local module can be flexibly integrated into existing deep networks for end-to-end training to capture deep feature correlation between each location and its neighborhood.
Ranked #1 on Grayscale Image Denoising on Set12 sigma30
no code implementations • ECCV 2018 • Guojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao, Chen Change Loy
We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors.
1 code implementation • ECCV 2018 • Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, Chen Change Loy
A transformer is subsequently used to adapt the boundary of source face to the boundary of target face.
2 code implementations • ECCV 2018 • Fei Wang, Liren Chen, Cheng Li, Shiyao Huang, Yanjie Chen, Chen Qian, Chen Change Loy
2) With the original datasets and cleaned subsets, we profile and analyze label noise properties of MegaFace and MS-Celeb-1M.
45 code implementations • 1 Sep 2018 • Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang
To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).
Ranked #2 on Face Hallucination on FFHQ 512 x 512 - 16x upscaling
no code implementations • ECCV 2018 • Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin
Lifelong learning aims at adapting a learned model to new tasks while retaining the knowledge gained earlier.
4 code implementations • ECCV 2018 • Hengshuang Zhao, Yi Zhang, Shu Liu, Jianping Shi, Chen Change Loy, Dahua Lin, Jiaya Jia
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #51 on Semantic Segmentation on Cityscapes test
4 code implementations • ECCV 2018 • Xiaohang Zhan, Ziwei Liu, Junjie Yan, Dahua Lin, Chen Change Loy
Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected.
no code implementations • 7 Sep 2018 • Yubin Deng, Ke Yu, Dahua Lin, Xiaoou Tang, Chen Change Loy
Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns.
no code implementations • 27 Sep 2018 • Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy
It is challenging to disentangle an object into two orthogonal spaces of structure and appearance since each can influence the visual observation in a different and unpredictable way.
2 code implementations • 7 Nov 2018 • Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy
In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction.
Ranked #1 on Steering Control on BDD100K val
2 code implementations • CVPR 2019 • Xintao Wang, Ke Yu, Chao Dong, Xiaoou Tang, Chen Change Loy
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect.
no code implementations • 30 Nov 2018 • Weidong Yin, Ziwei Liu, Chen Change Loy
Geometry-aware flow is able to warp the source face attribute into the target face context and generate a warp-and-blend result.
1 code implementation • 5 Dec 2018 • Mengya Gao, Yujun Shen, Quanquan Li, Junjie Yan, Liang Wan, Dahua Lin, Chen Change Loy, Xiaoou Tang
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
1 code implementation • CVPR 2019 • Jiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, Dahua Lin
State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.
Ranked #1 on Region Proposal on COCO test-dev
5 code implementations • CVPR 2019 • Kai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.
Ranked #32 on Object Detection on COCO-O
no code implementations • 19 Feb 2019 • Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jian-Feng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
no code implementations • 3 Mar 2019 • Lu Sheng, Junting Pan, Jiaming Guo, Jing Shao, Xiaogang Wang, Chen Change Loy
Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions.
3 code implementations • 15 Mar 2019 • Tak-Wai Hui, Xiaoou Tang, Chen Change Loy
Over four decades, the majority addresses the problem of optical flow estimation using variational methods.
Ranked #6 on Optical Flow Estimation on KITTI 2012
1 code implementation • CVPR 2019 • Xiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy
Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem.
1 code implementation • CVPR 2019 • Yining Li, Chen Huang, Chen Change Loy
Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.
3 code implementations • CVPR 2019 • Lei Yang, Xiaohang Zhan, Dapeng Chen, Junjie Yan, Chen Change Loy, Dahua Lin
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
1 code implementation • CVPR 2020 • Yuhang Cao, Kai Chen, Chen Change Loy, Dahua Lin
Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector.
no code implementations • CVPR 2019 • Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy
Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks.
1 code implementation • 23 Apr 2019 • Ke Yu, Xintao Wang, Chao Dong, Xiaoou Tang, Chen Change Loy
To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region.
3 code implementations • ICCV 2019 • Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin
CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.
Ranked #3 on Feature Upsampling on ImageNet
11 code implementations • 7 May 2019 • Xintao Wang, Kelvin C. K. Chan, Ke Yu, Chao Dong, Chen Change Loy
In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges.
Ranked #2 on Deblurring on REDS
2 code implementations • CVPR 2019 • Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy
Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.
Ranked #8 on Video Inpainting on DAVIS
One-shot visual object segmentation Optical Flow Estimation +2
1 code implementation • ICLR Workshop DeepGenStruct 2019 • Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably.
144 code implementations • 17 Jun 2019 • Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, Zheng Zhang, Dazhi Cheng, Chenchen Zhu, Tianheng Cheng, Qijie Zhao, Buyu Li, Xin Lu, Rui Zhu, Yue Wu, Jifeng Dai, Jingdong Wang, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin
In this paper, we introduce the various features of this toolbox.
2 code implementations • ICCV 2019 • Yuenan Hou, Zheng Ma, Chunxiao Liu, Chen Change Loy
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations.
Ranked #5 on Lane Detection on BDD100K val
2 code implementations • 5 Aug 2019 • Yunxuan Zhang, Siwei Zhang, Yue He, Cheng Li, Chen Change Loy, Ziwei Liu
However, in real-world scenario end-users often only have one target face at hand, rendering existing methods inapplicable.
1 code implementation • ICCV 2019 • Yu Rong, Ziwei Liu, Cheng Li, Kaidi Cao, Chen Change Loy
Specifically, we focus on the challenging task of in-the-wild 3D human recovery from single images when paired 3D annotations are not fully available.
1 code implementation • ICCV 2019 • Wenwei Zhang, Hui Zhou, Shuyang Sun, Zhe Wang, Jianping Shi, Chen Change Loy
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects.
Ranked #10 on Multiple Object Tracking on KITTI Tracking test
no code implementations • 18 Nov 2019 • Wu Shi, Tak-Wai Hui, Ziwei Liu, Dahua Lin, Chen Change Loy
Another important observation is that fashion textures are multi-modal.
3 code implementations • ECCV 2020 • Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin
To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket.
no code implementations • CVPR 2020 • Dongzhan Zhou, Xinchi Zhou, Wenwei Zhang, Chen Change Loy, Shuai Yi, Xuesen Zhang, Wanli Ouyang
While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming.
1 code implementation • CVPR 2020 • Liming Jiang, Ren Li, Wayne Wu, Chen Qian, Chen Change Loy
The quality of generated videos outperforms those in existing datasets, validated by user studies.
no code implementations • 15 Jan 2020 • Linsen Song, Wayne Wu, Chen Qian, Ran He, Chen Change Loy
The audio-translated expression parameters are then used to synthesize a photo-realistic human subject in each video frame, with the movement of the mouth regions precisely mapped to the source audio.
9 code implementations • CVPR 2020 • Chunle Guo, Chongyi Li, Jichang Guo, Chen Change Loy, Junhui Hou, Sam Kwong, Runmin Cong
The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
Ranked #1 on Color Constancy on INTEL-TUT2
2 code implementations • ICLR 2020 • Yuanbo Xiangli, Yubin Deng, Bo Dai, Chen Change Loy, Dahua Lin
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles.
no code implementations • 21 Feb 2020 • Mengya Gao, Yujun Shen, Quanquan Li, Chen Change Loy
Knowledge distillation (KD) is one of the most potent ways for model compression.
2 code implementations • 17 Mar 2020 • Yu Liu, Guanglu Song, Yuhang Zang, Yan Gao, Enze Xie, Junjie Yan, Chen Change Loy, Xiaogang Wang
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
1 code implementation • ECCV 2020 • Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo
Learning a good image prior is a long-term goal for image restoration and manipulation.
no code implementations • CVPR 2020 • Zhuoqian Yang, Wentao Zhu, Wayne Wu, Chen Qian, Qiang Zhou, Bolei Zhou, Chen Change Loy
We present a lightweight video motion retargeting approach TransMoMo that is capable of transferring motion of a person in a source video realistically to another video of a target person.
3 code implementations • CVPR 2020 • Lei Yang, Dapeng Chen, Xiaohang Zhan, Rui Zhao, Chen Change Loy, Dahua Lin
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
2 code implementations • CVPR 2020 • Xiaohang Zhan, Xingang Pan, Bo Dai, Ziwei Liu, Dahua Lin, Chen Change Loy
This is achieved via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner.
1 code implementation • 7 Apr 2020 • Kai Chen, Yuhang Cao, Chen Change Loy, Dahua Lin, Christoph Feichtenhofer
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale.
1 code implementation • CVPR 2020 • Yuenan Hou, Zheng Ma, Chunxiao Liu, Tak-Wai Hui, Chen Change Loy
We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation.
Ranked #1 on Semantic Segmentation on ApolloScape
2 code implementations • ECCV 2020 • Guodong Xu, Ziwei Liu, Xiaoxiao Li, Chen Change Loy
Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning.
Ranked #32 on Knowledge Distillation on ImageNet
1 code implementation • CVPR 2020 • Xiaohang Zhan, Jiahao Xie, Ziwei Liu, Yew Soon Ong, Chen Change Loy
In this way, labels and the network evolve shoulder-to-shoulder rather than alternatingly.
1 code implementation • NeurIPS 2020 • Shangchen Zhou, Jiawei Zhang, WangMeng Zuo, Chen Change Loy
Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image.
1 code implementation • ECCV 2020 • Chongyi Li, Runmin Cong, Yongri Piao, Qianqian Xu, Chen Change Loy
Second, we propose an adaptive feature selection (AFS) module to select saliency-related features and suppress the inferior ones.
Ranked #8 on RGB-D Salient Object Detection on NJU2K
1 code implementation • ECCV 2020 • Tak-Wai Hui, Chen Change Loy
The keys to success lie in the use of cost volume and coarse-to-fine flow inference.
Ranked #4 on Optical Flow Estimation on KITTI 2012
1 code implementation • ECCV 2020 • Liming Jiang, Changxu Zhang, Mingyang Huang, Chunxiao Liu, Jianping Shi, Chen Change Loy
We introduce a simple and versatile framework for image-to-image translation.
no code implementations • ECCV 2020 • Zhongang Cai, Junzhe Zhang, Daxuan Ren, Cunjun Yu, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Chen Change Loy
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views.
2 code implementations • CVPR 2021 • Jiaqi Wang, Wenwei Zhang, Yuhang Zang, Yuhang Cao, Jiangmiao Pang, Tao Gong, Kai Chen, Ziwei Liu, Chen Change Loy, Dahua Lin
Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories.
2 code implementations • 26 Aug 2020 • Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy
In this work, we present a comprehensive empirical study to better understand the role of inter-image invariance learning from three main constituting components: pseudo-label maintenance, sampling strategy, and decision boundary design.
no code implementations • 15 Sep 2020 • Kelvin C. K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.
1 code implementation • 28 Sep 2020 • Rui Xu, Minghao Guo, Jiaqi Wang, Xiaoxiao Li, Bolei Zhou, Chen Change Loy
By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions.
no code implementations • 26 Oct 2020 • Chongyi Li, Chunle Guo, Qiming Ai, Shangchen Zhou, Chen Change Loy
This paper presents a new method, called FlexiCurve, for photo enhancement.
1 code implementation • ICLR 2021 • Xingang Pan, Bo Dai, Ziwei Liu, Chen Change Loy, Ping Luo
Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner.
no code implementations • CVPR 2021 • Kelvin C. K. Chan, Xintao Wang, Xiangyu Xu, Jinwei Gu, Chen Change Loy
We show that pre-trained Generative Adversarial Networks (GANs), e. g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR).
6 code implementations • CVPR 2021 • Kelvin C. K. Chan, Xintao Wang, Ke Yu, Chao Dong, Chen Change Loy
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension.
no code implementations • 7 Dec 2020 • Jiaqi Wang, Kai Chen, Rui Xu, Ziwei Liu, Chen Change Loy, Dahua Lin
Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.
no code implementations • CVPR 2021 • Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, Chen Change Loy
In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.
1 code implementation • 17 Dec 2020 • Guodong Xu, Ziwei Liu, Chen Change Loy
Our goal is to achieve a performance comparable to conventional knowledge distillation with a lower computation cost during training.
1 code implementation • ICCV 2021 • Liming Jiang, Bo Dai, Wayne Wu, Chen Change Loy
In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further.
8 code implementations • 23 Dec 2020 • Wenwei Zhang, Zhe Wang, Chen Change Loy
Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation.
no code implementations • 29 Dec 2020 • Yu Rong, Ziwei Liu, Chen Change Loy
The reason is that most of the current models perform regression based on a single human prototype, which is similar to common poses while far from the rare poses.
2 code implementations • 18 Feb 2021 • Liming Jiang, Zhengkui Guo, Wayne Wu, Zhaoyang Liu, Ziwei Liu, Chen Change Loy, Shuo Yang, Yuanjun Xiong, Wei Xia, Baoying Chen, Peiyu Zhuang, Sili Li, Shen Chen, Taiping Yao, Shouhong Ding, Jilin Li, Feiyue Huang, Liujuan Cao, Rongrong Ji, Changlei Lu, Ganchao Tan
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
1 code implementation • ICCV 2021 • Yuhang Zang, Chen Huang, Chen Change Loy
We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes.
4 code implementations • 1 Mar 2021 • Chongyi Li, Chunle Guo, Chen Change Loy
This paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
1 code implementation • 2 Mar 2021 • Yuenan Hou, Zheng Ma, Chunxiao Liu, Zhe Wang, Chen Change Loy
Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network.
2 code implementations • 3 Mar 2021 • Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, Chen Change Loy
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce.
1 code implementation • CVPR 2021 • Li SiYao, Shiyu Zhao, Weijiang Yu, Wenxiu Sun, Dimitris N. Metaxas, Chen Change Loy, Ziwei Liu
In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming.
1 code implementation • 7 Apr 2021 • Linsen Song, Wayne Wu, Chaoyou Fu, Chen Qian, Chen Change Loy, Ran He
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
1 code implementation • CVPR 2021 • Xinya Ji, Hang Zhou, Kaisiyuan Wang, Wayne Wu, Chen Change Loy, Xun Cao, Feng Xu
In this work, we present Emotional Video Portraits (EVP), a system for synthesizing high-quality video portraits with vivid emotional dynamics driven by audios.
1 code implementation • CVPR 2021 • Ruicheng Feng, Chongyi Li, Huaijin Chen, Shuai Li, Chen Change Loy, Jinwei Gu
Recent development of Under-Display Camera (UDC) systems provides a true bezel-less and notch-free viewing experience on smartphones (and TV, laptops, tablets), while allowing images to be captured from the selfie camera embedded underneath.
3 code implementations • 21 Apr 2021 • Chongyi Li, Chunle Guo, Linghao Han, Jun Jiang, Ming-Ming Cheng, Jinwei Gu, Chen Change Loy
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination.
1 code implementation • 21 Apr 2021 • Ren Yang, Radu Timofte, Jing Liu, Yi Xu, Xinjian Zhang, Minyi Zhao, Shuigeng Zhou, Kelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy, Xin Li, Fanglong Liu, He Zheng, Lielin Jiang, Qi Zhang, Dongliang He, Fu Li, Qingqing Dang, Yibin Huang, Matteo Maggioni, Zhongqian Fu, Shuai Xiao, Cheng Li, Thomas Tanay, Fenglong Song, Wentao Chao, Qiang Guo, Yan Liu, Jiang Li, Xiaochao Qu, Dewang Hou, Jiayu Yang, Lyn Jiang, Di You, Zhenyu Zhang, Chong Mou, Iaroslav Koshelev, Pavel Ostyakov, Andrey Somov, Jia Hao, Xueyi Zou, Shijie Zhao, Xiaopeng Sun, Yiting Liao, Yuanzhi Zhang, Qing Wang, Gen Zhan, Mengxi Guo, Junlin Li, Ming Lu, Zhan Ma, Pablo Navarrete Michelini, Hai Wang, Yiyun Chen, Jingyu Guo, Liliang Zhang, Wenming Yang, Sijung Kim, Syehoon Oh, Yucong Wang, Minjie Cai, Wei Hao, Kangdi Shi, Liangyan Li, Jun Chen, Wei Gao, Wang Liu, XiaoYu Zhang, Linjie Zhou, Sixin Lin, Ru Wang
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
1 code implementation • CVPR 2021 • Hang Zhou, Yasheng Sun, Wayne Wu, Chen Change Loy, Xiaogang Wang, Ziwei Liu
While speech content information can be defined by learning the intrinsic synchronization between audio-visual modalities, we identify that a pose code will be complementarily learned in a modulated convolution-based reconstruction framework.
no code implementations • CVPR 2021 • Junzhe Zhang, Xinyi Chen, Zhongang Cai, Liang Pan, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Bo Dai, Chen Change Loy
In contrast to previous fully supervised approaches, in this paper we present ShapeInversion, which introduces Generative Adversarial Network (GAN) inversion to shape completion for the first time.
3 code implementations • CVPR 2022 • Kelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
We show that by empowering the recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively.
Ranked #1 on Video Enhancement on MFQE v2
2 code implementations • 1 Jun 2021 • Kaiyang Zhou, Chen Change Loy, Ziwei Liu
We find that the DG methods, which by design are unable to handle unlabeled data, perform poorly with limited labels in SSDG; the SSL methods, especially FixMatch, obtain much better results but are still far away from the basic vanilla model trained using full labels.
1 code implementation • CVPR 2021 • Yuming Jiang, Kelvin C. K. Chan, Xintao Wang, Chen Change Loy, Ziwei Liu
However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e. g. scale and rotation) and the resolution gap (e. g. HR and LR).
no code implementations • CVPR 2021 • Linsen Song, Wayne Wu, Chaoyou Fu, Chen Qian, Chen Change Loy, Ran He
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
1 code implementation • NeurIPS 2021 • Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy
Extensive experiments on COCO show that ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks.
1 code implementation • NeurIPS 2021 • Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class.
Ranked #7 on Panoptic Segmentation on COCO test-dev
13 code implementations • 2 Sep 2021 • Kaiyang Zhou, Jingkang Yang, Chen Change Loy, Ziwei Liu
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks.
Ranked #2 on Few-shot Age Estimation on MORPH Album2
1 code implementation • ICCV 2021 • Xiangyu Xu, Chen Change Loy
We propose a Transformer-based framework for 3D human texture estimation from a single image.
1 code implementation • ICCV 2021 • Yuming Jiang, Ziqi Huang, Xingang Pan, Chen Change Loy, Ziwei Liu
In this work, we propose Talk-to-Edit, an interactive facial editing framework that performs fine-grained attribute manipulation through dialog between the user and the system.
Ranked #1 on Fine-Grained Facial Editing on CelebA-Dialog
1 code implementation • ICCV 2021 • Ke Yu, Zexian Li, Yue Peng, Chen Change Loy, Jinwei Gu
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand.
no code implementations • 29 Sep 2021 • Guodong Xu, Yuenan Hou, Ziwei Liu, Chen Change Loy
To further enhance the semantic consistency between the teacher and student model, we present another latent-direction-based distillation loss that preserves the semantic relations in latent space.
no code implementations • 29 Sep 2021 • Junzhe Zhang, Daxuan Ren, Zhongang Cai, Chai Kiat Yeo, Bo Dai, Chen Change Loy
Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation.
no code implementations • 29 Sep 2021 • Yidi Shao, Chen Change Loy, Bo Dai
However, they force particles to interact with all neighbors without selection, and they fall short in capturing material semantics for different particles, leading to unsatisfactory performance, especially in generalization.
1 code implementation • 9 Oct 2021 • Yihao Liu, Hengyuan Zhao, Kelvin C. K. Chan, Xintao Wang, Chen Change Loy, Yu Qiao, Chao Dong
We address this problem from a new perspective, by jointly considering colorization and temporal consistency in a unified framework.
no code implementations • 14 Oct 2021 • Zhongang Cai, Mingyuan Zhang, Jiawei Ren, Chen Wei, Daxuan Ren, Zhengyu Lin, Haiyu Zhao, Lei Yang, Chen Change Loy, Ziwei Liu
Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios.
no code implementations • 18 Oct 2021 • Linus Ericsson, Henry Gouk, Chen Change Loy, Timothy M. Hospedales
Self-supervised representation learning methods aim to provide powerful deep feature learning without the requirement of large annotated datasets, thus alleviating the annotation bottleneck that is one of the main barriers to practical deployment of deep learning today.
no code implementations • 25 Oct 2021 • Rui Xu, Xiangyu Xu, Kai Chen, Bolei Zhou, Chen Change Loy
Transformer becomes prevalent in computer vision, especially for high-level vision tasks.
1 code implementation • NeurIPS 2021 • Xingang Pan, Xudong Xu, Chen Change Loy, Christian Theobalt, Bo Dai
Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint as regularization to learn valid 3D radiance fields from 2D images.
no code implementations • 1 Nov 2021 • Yu Rong, Jingbo Wang, Ziwei Liu, Chen Change Loy
In this paper, we make the first attempt to reconstruct 3D interacting hands from monocular single RGB images.
2 code implementations • NeurIPS 2021 • Liming Jiang, Bo Dai, Wayne Wu, Chen Change Loy
Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images.
1 code implementation • CVPR 2022 • Kelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
The diversity and complexity of degradations in real-world video super-resolution (VSR) pose non-trivial challenges in inference and training.
1 code implementation • 2 Dec 2021 • Chong Zhou, Chen Change Loy, Bo Dai
Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition.
no code implementations • 19 Dec 2021 • Wentao Zhu, Zhuoqian Yang, Ziang Di, Wayne Wu, Yizhou Wang, Chen Change Loy
Trained with the canonicalization operations and the derived regularizations, our method learns to factorize a skeleton sequence into three independent semantic subspaces, i. e., motion, structure, and view angle.
1 code implementation • 7 Feb 2022 • Shangchen Zhou, Chongyi Li, Chen Change Loy
With the pipeline, we present the first large-scale dataset for joint low-light enhancement and deblurring.
Ranked #2 on Low-Light Image Enhancement on Sony-Total-Dark
9 code implementations • CVPR 2022 • Kaiyang Zhou, Jingkang Yang, Chen Change Loy, Ziwei Liu
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets.
Ranked #3 on Prompt Engineering on ImageNet V2
1 code implementation • 21 Mar 2022 • Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency.
Ranked #2 on Unsupervised Semantic Segmentation on COCO-All (mIoU metric)
1 code implementation • 22 Mar 2022 • Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy
To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.
Ranked #21 on Open Vocabulary Object Detection on MSCOCO
1 code implementation • CVPR 2022 • Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data.
1 code implementation • CVPR 2022 • Li SiYao, Weijiang Yu, Tianpei Gu, Chunze Lin, Quan Wang, Chen Qian, Chen Change Loy, Ziwei Liu
With the learned choreographic memory, dance generation is realized on the quantized units that meet high choreography standards, such that the generated dancing sequences are confined within the spatial constraints.
Ranked #1 on Motion Synthesis on AIST++
1 code implementation • CVPR 2022 • Yanbo Xu, Yueqin Yin, Liming Jiang, Qianyi Wu, Chengyao Zheng, Chen Change Loy, Bo Dai, Wayne Wu
In this study, we highlight the importance of interaction in a dual-space GAN for more controllable editing.
1 code implementation • CVPR 2022 • Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy
In this work, we present a novel framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), to improve the overall quality and applicability of the translation algorithm.
1 code implementation • CVPR 2022 • Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, Chen Change Loy
We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design.
Ranked #1 on Video Panoptic Segmentation on KITTI-STEP (using extra training data)
1 code implementation • 11 Apr 2022 • Kelvin C. K. Chan, Shangchen Zhou, Xiangyu Xu, Chen Change Loy
The exploitation of long-term information has been a long-standing problem in video restoration.
4 code implementations • 25 Apr 2022 • Jianglin Fu, Shikai Li, Yuming Jiang, Kwan-Yee Lin, Chen Qian, Chen Change Loy, Wayne Wu, Ziwei Liu
In addition, a model zoo and human editing applications are demonstrated to facilitate future research in the community.
no code implementations • 28 Apr 2022 • Zhongang Cai, Daxuan Ren, Ailing Zeng, Zhengyu Lin, Tao Yu, Wenjia Wang, Xiangyu Fan, Yang Gao, Yifan Yu, Liang Pan, Fangzhou Hong, Mingyuan Zhang, Chen Change Loy, Lei Yang, Ziwei Liu
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications.
3 code implementations • 12 May 2022 • Kenny T. R. Voo, Liming Jiang, Chen Change Loy
This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications.
2 code implementations • 31 May 2022 • Yuming Jiang, Shuai Yang, Haonan Qiu, Wayne Wu, Chen Change Loy, Ziwei Liu
In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation.
no code implementations • CVPR 2022 • Yuenan Hou, Xinge Zhu, Yuexin Ma, Chen Change Loy, Yikang Li
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.
Ranked #8 on LIDAR Semantic Segmentation on nuScenes (val mIoU metric)
3 code implementations • 15 Jun 2022 • Jiahao Xie, Wei Li, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy
We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models.
1 code implementation • 22 Jun 2022 • Shangchen Zhou, Kelvin C. K. Chan, Chongyi Li, Chen Change Loy
In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces.
Ranked #1 on Blind Face Restoration on CelebA-Test
1 code implementation • 20 Jul 2022 • Davide Moltisanti, Jinyi Wu, Bo Dai, Chen Change Loy
Estimating human keypoints from these videos is difficult due to the complexity of the dance, as well as the multiple moving cameras recording setup.
1 code implementation • 20 Jul 2022 • Junzhe Zhang, Daxuan Ren, Zhongang Cai, Chai Kiat Yeo, Bo Dai, Chen Change Loy
Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation.
1 code implementation • 22 Jul 2022 • Yidi Shao, Chen Change Loy, Bo Dai
Consequently, in this paper we propose a novel Transformer-based method, dubbed as Transformer with Implicit Edges (TIE), to capture the rich semantics of particle interactions in an edge-free manner.
1 code implementation • 25 Jul 2022 • Jianyi Wang, Kelvin C. K. Chan, Chen Change Loy
Measuring the perception of visual content is a long-standing problem in computer vision.
Ranked #9 on Video Quality Assessment on MSU SR-QA Dataset
1 code implementation • 25 Jul 2022 • Hao Zhu, Wayne Wu, Wentao Zhu, Liming Jiang, Siwei Tang, Li Zhang, Ziwei Liu, Chen Change Loy
Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields.
Ranked #1 on Unconditional Video Generation on CelebV-HQ
no code implementations • 28 Jul 2022 • Chongyi Li, Chunle Guo, Ruicheng Feng, Shangchen Zhou, Chen Change Loy
Our method inherits the zero-reference learning and curve-based framework from an effective low-light image enhancement method, Zero-DCE, with further speed up in its inference speed, reduction in its model size, and extension to controllable exposure adjustment.
1 code implementation • 29 Jul 2022 • Kelvin C. K. Chan, Xiangyu Xu, Xintao Wang, Jinwei Gu, Chen Change Loy
While most existing perceptual-oriented approaches attempt to generate realistic outputs through learning with adversarial loss, our method, Generative LatEnt bANk (GLEAN), goes beyond existing practices by directly leveraging rich and diverse priors encapsulated in a pre-trained GAN.
1 code implementation • 29 Jul 2022 • Guangcong Wang, Yinuo Yang, Chen Change Loy, Ziwei Liu
To tackle this problem, we propose a coupled dual-StyleGAN panorama synthesis network (StyleLight) that integrates LDR and HDR panorama synthesis into a unified framework.
1 code implementation • 18 Aug 2022 • Guodong Xu, Yuenan Hou, Ziwei Liu, Chen Change Loy
To further enhance the semantic consistency between the teacher and student model, we present a latent-direction-based distillation loss that preserves the semantic relations in latent space.
2 code implementations • 15 Sep 2022 • Kaiyang Zhou, Yuanhan Zhang, Yuhang Zang, Jingkang Yang, Chen Change Loy, Ziwei Liu
Another interesting observation is that the teacher-student gap on out-of-distribution data is bigger than that on in-distribution data, which highlights the capacity mismatch issue as well as the shortcoming of KD.
1 code implementation • 15 Sep 2022 • Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu
A detailed description of all models developed in this challenge is provided in this paper.
1 code implementation • 15 Sep 2022 • Wenxiu Sun, Qingpeng Zhu, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu
A detailed description of all models developed in this challenge is provided in this paper.
1 code implementation • 15 Sep 2022 • Ruicheng Feng, Chongyi Li, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Jun Jiang, Qingyu Yang, Chen Change Loy, Jinwei Gu
In this paper, we summarize and review the Under-Display Camera (UDC) Image Restoration track on MIPI 2022.
1 code implementation • 15 Sep 2022 • Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu
A detailed description of all models developed in this challenge is provided in this paper.
1 code implementation • 15 Sep 2022 • Qingyu Yang, Guang Yang, Jun Jiang, Chongyi Li, Ruicheng Feng, Shangchen Zhou, Wenxiu Sun, Qingpeng Zhu, Chen Change Loy, Jinwei Gu
A detailed description of all models developed in this challenge is provided in this paper.
1 code implementation • 22 Sep 2022 • Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
1 code implementation • 11 Oct 2022 • Man Zhou, Hu Yu, Jie Huang, Feng Zhao, Jinwei Gu, Chen Change Loy, Deyu Meng, Chongyi Li
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
1 code implementation • 12 Oct 2022 • Yuekun Dai, Chongyi Li, Shangchen Zhou, Ruicheng Feng, Chen Change Loy
In this paper, we introduce, Flare7K, the first nighttime flare removal dataset, which is generated based on the observation and statistics of real-world nighttime lens flares.
Ranked #2 on Flare Removal on Flare7K
1 code implementation • 13 Oct 2022 • Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, Chen Change Loy
Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP.
1 code implementation • 10 Nov 2022 • Li SiYao, Yuhang Li, Bo Li, Chao Dong, Ziwei Liu, Chen Change Loy
Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations.
no code implementations • 12 Dec 2022 • Qixin Yan, Chunle Guo, Jixin Zhao, Yuekun Dai, Chen Change Loy, Chongyi Li
The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeup transfer, and enabling efficient makeup transfer via a single-path structure.
2 code implementations • 13 Dec 2022 • Zongsheng Yue, Chen Change Loy
Moreover, the transition distribution can contract the error of the restoration backbone and thus makes our method more robust to unknown degradations.
Ranked #5 on Blind Face Restoration on CelebA-Test
no code implementations • CVPR 2023 • Yushi Lan, Xuyi Meng, Shuai Yang, Chen Change Loy, Bo Dai
In this paper, we study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
1 code implementation • 19 Dec 2022 • Yuming Jiang, Kelvin C. K. Chan, Xintao Wang, Chen Change Loy, Ziwei Liu
To tackle these challenges, we propose C2-Matching in this work, which performs explicit robust matching crossing transformation and resolution.
no code implementations • 19 Dec 2022 • Yushi Lan, Chen Change Loy, Bo Dai
The neural radiance field (NeRF) has shown promising results in preserving the fine details of objects and scenes.
no code implementations • ICCV 2023 • Junzhe Zhang, Yushi Lan, Shuai Yang, Fangzhou Hong, Quan Wang, Chai Kiat Yeo, Ziwei Liu, Chen Change Loy
In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture.
2 code implementations • ICCV 2023 • Jianzong Wu, Xiangtai Li, Henghui Ding, Xia Li, Guangliang Cheng, Yunhai Tong, Chen Change Loy
Experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS) demonstrate the superiority of the CGG.