no code implementations • ICML 2020 • Xiangyu Xu, Yongrui Ma, Wenxiu Sun
In this work, we propose to learn the weight matrix for joint image filtering.
no code implementations • ECCV 2020 • Quewei Li, Jie Guo, Yang Fei, Qinyu Tang, Wenxiu Sun, Jin Zeng, Yanwen Guo
We propose a deep convolutional neural network (CNN) to estimate surface normal from a single color image accompanied with a low-quality depth channel.
no code implementations • 8 Jul 2022 • Liang Liao, Kangmin Xu, HaoNing Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, Weisi Lin
Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.
1 code implementation • 6 Jul 2022 • HaoNing Wu, Chaofeng Chen, Jingwen Hou, Liang Liao, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin
Consisting of fragments and FANet, the proposed FrAgment Sample Transformer for VQA (FAST-VQA) enables efficient end-to-end deep VQA and learns effective video-quality-related representations.
Ranked #1 on
Video Quality Assessment
on YouTube-UGC
(using extra training data)
no code implementations • 20 Jun 2022 • HaoNing Wu, Chaofeng Chen, Liang Liao, Jingwen Hou, Wenxiu Sun, Qiong Yan, Weisi Lin
Based on prominent time-series modeling ability of transformers, we propose a novel and effective transformer-based VQA method to tackle these two issues.
1 code implementation • ICCV 2021 • Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li
On the contrary, the soft composition operates by stitching different patches into a whole feature map where pixels in overlapping regions are summed up.
Ranked #2 on
Video Inpainting
on DAVIS
2 code implementations • ICCV 2021 • Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan, Qifeng Chen
We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results.
no code implementations • 7 Aug 2021 • Chenyang Lei, Xuhua Huang, Chenyang Qi, Yankun Zhao, Wenxiu Sun, Qiong Yan, Qifeng Chen
Due to the lack of a large-scale reflection removal dataset with diverse real-world scenes, many existing reflection removal methods are trained on synthetic data plus a small amount of real-world data, which makes it difficult to evaluate the strengths or weaknesses of different reflection removal methods thoroughly.
1 code implementation • 14 Apr 2021 • Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li
Seamless combination of these two novel designs forms a better spatial-temporal attention scheme and our proposed model achieves better performance than state-of-the-art video inpainting approaches with significant boosted efficiency.
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 • CVPR 2021 • Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun
For the current query frame, the query regions are tracked and predicted based on the optical flow estimated from the previous frame.
One-shot visual object segmentation
Optical Flow Estimation
+2
3 code implementations • ICLR 2021 • Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li
In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network, which can maintain the advantages of both unstructured fine-grained sparsity and structured coarse-grained sparsity simultaneously on specifically designed GPUs.
1 code implementation • 2 Feb 2021 • Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang
In this paper, we study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images.
no code implementations • 26 Jan 2021 • Ju He, Enyu Zhou, Liusheng Sun, Fei Lei, Chenyang Liu, Wenxiu Sun
Though synthetic dataset is proposed to fill the gaps of large data demand, the fine-tuning on real dataset is still needed due to the domain variances between synthetic data and real data.
3 code implementations • 26 Jan 2021 • Xiangyu Xu, Muchen Li, Wenxiu Sun, Ming-Hsuan Yang
We present a spatial pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising.
2 code implementations • 10 Sep 2020 • Yihao Liu, Liangbin Xie, Li Si-Yao, Wenxiu Sun, Yu Qiao, Chao Dong
In this work, we further improve the performance of QVI from three facets and propose an enhanced quadratic video interpolation (EQVI) model.
no code implementations • 12 Aug 2020 • Di Qiu, Jin Zeng, Zhanghan Ke, Wenxiu Sun, Chengxi Yang
By incorporating the depth map, our approach is able to extrapolate realistic high-frequency effects under novel lighting via geometry guided image decomposition from the flashlight image, and predict the cast shadow map from the shadow-encoding transformed depth map.
3 code implementations • 22 Jun 2020 • Haozhe Xie, Hongxun Yao, Shengping Zhang, Shangchen Zhou, Wenxiu Sun
A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume.
Ranked #1 on
3D Object Reconstruction
on Data3D−R2N2
1 code implementation • ECCV 2020 • Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, Wenxiu Sun
In particular, we devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information.
Ranked #1 on
Point Cloud Completion
on Completion3D
no code implementations • CVPR 2020 • Rui Liu, Chengxi Yang, Wenxiu Sun, Xiaogang Wang, Hongsheng Li
Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias.
1 code implementation • CVPR 2020 • Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan, Wenxiu Sun, Qifeng Chen
We present a novel formulation to removing reflection from polarized images in the wild.
1 code implementation • NeurIPS 2019 • Xiangyu Xu, Li Si-Yao, Wenxiu Sun, Qian Yin, Ming-Hsuan Yang
Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors.
1 code implementation • 18 Oct 2019 • Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Xiaoshuai Sun, Wenxiu Sun
Inferring the 3D shape of an object from an RGB image has shown impressive results, however, existing methods rely primarily on recognizing the most similar 3D model from the training set to solve the problem.
1 code implementation • ICCV 2019 • Di Qiu, Jiahao Pang, Wenxiu Sun, Chengxi Yang
Recently, it is increasingly popular to equip mobile RGB cameras with Time-of-Flight (ToF) sensors for active depth sensing.
1 code implementation • CVPR 2019 • Xiangyu Xu, Yongrui Ma, Wenxiu Sun
Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input.
2 code implementations • 15 Apr 2019 • Xiangyu Xu, Muchen Li, Wenxiu Sun
Most of the classical denoising methods restore clear results by selecting and averaging pixels in the noisy input.
1 code implementation • CVPR 2019 • Jin Zeng, Yanfeng Tong, Yunmu Huang, Qiong Yan, Wenxiu Sun, Jing Chen, Yongtian Wang
The growing availability of commodity RGB-D cameras has boosted the applications in the field of scene understanding.
1 code implementation • 26 Sep 2018 • Ruichao Xiao, Wenxiu Sun, Jiahao Pang, Qiong Yan, Jimmy Ren
Our method is evaluated on both real-istic and synthetic stereo image pairs, and produces supe-rior results compared to the calibrated rectification or otherself-rectification approaches
no code implementations • 25 Sep 2018 • Ruichao Xiao, Wenxiu Sun, Chengxi Yang
Intuitively, the vari-ance in the Laplacian distribution is large for low confidentpixels while small for high-confidence pixels.
no code implementations • ECCV 2018 • Yukang Gan, Xiangyu Xu, Wenxiu Sun, Liang Lin
While significant progress has been made in monocular depth estimation with Convolutional Neural Networks (CNNs) extracting absolute features, such as edges and textures, the depth constraint of neighboring pixels, namely relative features, has been mostly ignored by recent methods.
1 code implementation • 31 Jul 2018 • Jin Zeng, Jiahao Pang, Wenxiu Sun, Gene Cheung
In this work, we combine the robustness merit of model-based approaches and the learning power of data-driven approaches for real image denoising.
1 code implementation • CVPR 2018 • Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, Liang Lin
By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details.
1 code implementation • CVPR 2018 • Yue Luo, Jimmy Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin
The resulting model outperforms all the previous monocular depth estimation methods as well as the stereo block matching method in the challenging KITTI dataset by only using a small number of real training data.
Ranked #18 on
Monocular Depth Estimation
on KITTI Eigen split
(using extra training data)
1 code implementation • CVPR 2018 • Yue Luo, Jimmy Ren, Zhouxia Wang, Wenxiu Sun, Jinshan Pan, Jianbo Liu, Jiahao Pang, Liang Lin
Such suboptimal results are mainly attributed to the inability of imposing sequential geometric consistency, handling severe image quality degradation (e. g. motion blur and occlusion) as well as the inability of capturing the temporal correlation among video frames.
Ranked #2 on
Pose Estimation
on J-HMDB
no code implementations • 1 Oct 2017 • Hui Yang, Jinshan Pan, Qiong Yan, Wenxiu Sun, Jimmy Ren, Yu-Wing Tai
In this paper, we introduce a bilinear composition loss function to address the problem of image dehazing.
1 code implementation • 30 Aug 2017 • Jiahao Pang, Wenxiu Sun, Jimmy SJ. Ren, Chengxi Yang, Qiong Yan
As opposed to directly learning the disparity at the second stage, we show that residual learning provides more effective refinement.
no code implementations • 30 May 2017 • Jimmy Ren, ZHIYANG YU, Jianbo Liu, Rui Zhang, Wenxiu Sun, Jiahao Pang, Xiaohao Chen, Qiong Yan
Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative trackers.
2 code implementations • CVPR 2017 • Jimmy Ren, Xiaohao Chen, Jianbo Liu, Wenxiu Sun, Jiahao Pang, Qiong Yan, Yu-Wing Tai, Li Xu
In this paper, we proposed a novel single stage end-to-end trainable object detection network to overcome this limitation.
no code implementations • 13 Feb 2016 • Jimmy Ren, Yongtao Hu, Yu-Wing Tai, Chuan Wang, Li Xu, Wenxiu Sun, Qiong Yan
This task not only requires collective perception over both visual and auditory signals, the robustness to handle severe quality degradations and unconstrained content variations are also indispensable.
1 code implementation • NeurIPS 2015 • Jimmy SJ. Ren, Li Xu, Qiong Yan, Wenxiu Sun
In this paper, we draw on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network.