no code implementations • 24 Mar 2024 • Haoyuan Wang, WenBo Hu, Lei Zhu, Rynson W. H. Lau
Our method has two stages: the geometry of the target object and the pre-filtered environmental radiance fields are reconstructed in the first stage, and materials of the target object are estimated in the second stage with the proposed NeP and material-aware cone sampling strategy.
no code implementations • 22 Mar 2024 • Zhenwei Wang, Tengfei Wang, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau
To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage.
no code implementations • 1 Mar 2024 • Yuhao Liu, Zhanghan Ke, Fang Liu, Nanxuan Zhao, Rynson W. H. Lau
Diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis.
1 code implementation • 22 Feb 2024 • Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson W. H. Lau
Practical large language model (LLM) services may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across numerous requests.
1 code implementation • 21 Feb 2024 • Huankang Guan, Ke Xu, Rynson W. H. Lau
Our key insight to this problem is that existing methods typically learn discriminative shadow features from the whole image globally, covering the full range of intensity values, and may not learn the subtle differences between shadow and non-shadow pixels in dark regions.
no code implementations • 1 Feb 2024 • Yuhao Liu, Zhanghan Ke, Ke Xu, Fang Liu, Zhenwei Wang, Rynson W. H. Lau
Based on this observation, we propose to condition the restoration of attenuated textures on the corrected local lighting in the shadow region.
1 code implementation • 11 Dec 2023 • Tianyu Huang, Yihan Zeng, Zhilu Zhang, Wan Xu, Hang Xu, Songcen Xu, Rynson W. H. Lau, WangMeng Zuo
The priors are then regarded as input conditions to maintain reasonable geometries, in which conditional LoRA and weighted score are further proposed to optimize detailed textures.
no code implementations • 29 Sep 2023 • Tianyu Huang, Yihan Zeng, Bowen Dong, Hang Xu, Songcen Xu, Rynson W. H. Lau, WangMeng Zuo
To this end, an NTFGen module is proposed to model general text latent code in noisy fields.
no code implementations • 6 Aug 2023 • Zhenwei Wang, Nanxuan Zhao, Gerhard Hancke, Rynson W. H. Lau
We also introduce an approach for generating a synthetic graphic design dataset with instructions to enable model training.
1 code implementation • CVPR 2023 • Zhanghan Ke, Yuhao Liu, Lei Zhu, Nanxuan Zhao, Rynson W. H. Lau
In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed.
no code implementations • 9 Jan 2023 • Yuhao Liu, Qing Guo, Lan Fu, Zhanghan Ke, Ke Xu, Wei Feng, Ivor W. Tsang, Rynson W. H. Lau
Hence, in this paper, we propose to remove shadows at the image structure level.
1 code implementation • 28 Nov 2022 • Ruozhen He, Jiaying Lin, Rynson W. H. Lau
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network.
1 code implementation • ICCV 2023 • Tianyu Huang, Bowen Dong, Yunhan Yang, Xiaoshui Huang, Rynson W. H. Lau, Wanli Ouyang, WangMeng Zuo
To address this issue, we propose CLIP2Point, an image-depth pre-training method by contrastive learning to transfer CLIP to the 3D domain, and adapt it to point cloud classification.
Ranked #3 on Training-free 3D Point Cloud Classification on ScanObjectNN (using extra training data)
no code implementations • 10 Sep 2022 • Haiyang Mei, Xin Yang, Letian Yu, Qiang Zhang, Xiaopeng Wei, Rynson W. H. Lau
Glass is very common in our daily life.
1 code implementation • 16 Aug 2022 • Tao Yan, Mingyue Li, Bin Li, Yang Yang, Rynson W. H. Lau
However, making full use of the abundant information available from LFIs, such as 2D array of sub-views and the disparity map of each sub-view, for effective rain removal is still a challenging problem.
1 code implementation • 28 Jul 2022 • Ruozhen He, Qihua Dong, Jiaying Lin, Rynson W. H. Lau
To achieve this, we first relabel 4, 040 images in existing camouflaged object datasets with scribbles, which takes ~10s to label one image.
1 code implementation • 13 Jul 2022 • Tianyu Huang, Bowen Dong, Jiaying Lin, Xiaohui Liu, Rynson W. H. Lau, WangMeng Zuo
Mirror detection aims to identify the mirror regions in the given input image.
1 code implementation • 4 Jul 2022 • Zhanghan Ke, Chunyi Sun, Lei Zhu, Ke Xu, Rynson W. H. Lau
Unlike prior methods that are based on black-box autoencoders, Harmonizer contains a neural network for filter argument prediction and several white-box filters (based on the predicted arguments) for image harmonization.
Ranked #7 on Image Harmonization on iHarmony4
no code implementations • 22 Jun 2022 • Jiaying Lin, Yuen Hei Yeung, Rynson W. H. Lau
This however poses substantial challenges on the operations of autonomous systems such as robots, self-driving cars and drones, as the glass panels can become transparent obstacles to the navigation. Existing works attempt to exploit various cues, including glass boundary context or reflections, as a prior.
no code implementations • 31 Mar 2022 • Jiaying Lin, Huankang Guan, Rynson W. H. Lau
Salient Object Ranking (SOR) involves ranking the degree of saliency of multiple salient objects in an input image.
1 code implementation • CVPR 2022 • Xin Tian, Ke Xu, Xin Yang, Lin Du, BaoCai Yin, Rynson W. H. Lau
We observe that spatial attention works concurrently with object-based attention in the human visual recognition system.
no code implementations • 3 Dec 2021 • Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson W. H. Lau
Our key idea is to exploit the complementary properties of depth denoising and 3D reconstruction, for learning a two-scale PIFu representation to reconstruct high-frequency facial details and consistent bodies separately.
no code implementations • 19 Nov 2021 • Xin Tian, Ke Xu, Xin Yang, BaoCai Yin, Rynson W. H. Lau
However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels.
1 code implementation • 24 Sep 2021 • Jiayu Sun, Zhanghan Ke, Lihe Zhang, Huchuan Lu, Rynson W. H. Lau
In this work, we observe that instead of asking the user to explicitly provide a background image, we may recover it from the input video itself.
no code implementations • 31 Mar 2021 • Xin Yang, Yu Qiao, Shaozhe Chen, Shengfeng He, BaoCai Yin, Qiang Zhang, Xiaopeng Wei, Rynson W. H. Lau
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.
no code implementations • 26 Jan 2021 • Xin Yang, Zongliang Ma, Letian Yu, Ying Cao, BaoCai Yin, Xiaopeng Wei, Qiang Zhang, Rynson W. H. Lau
Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios.
no code implementations • 4 Jan 2021 • Xiaoyang Zheng, Xin Tan, Jie zhou, Lizhuang Ma, Rynson W. H. Lau
This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class.
1 code implementation • ICCV 2021 • Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson W. H. Lau
It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.
9 code implementations • 24 Nov 2020 • Zhanghan Ke, Jiayu Sun, Kaican Li, Qiong Yan, Rynson W. H. Lau
MODNet is easy to be trained in an end-to-end manner.
Ranked #1 on Image Matting on PPM-100
no code implementations • 29 Sep 2020 • Xin Tian, Ke Xu, Xin Yang, Bao-Cai Yin, Rynson W. H. Lau
Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.
1 code implementation • ECCV 2020 • Zhanghan Ke, Di Qiu, Kaican Li, Qiong Yan, Rynson W. H. Lau
Although SSL methods have achieved impressive results in image classification, the performances of applying them to pixel-wise tasks are unsatisfactory due to their need for dense outputs.
1 code implementation • 3 Jul 2020 • Yuzhen Niu, Jianbin Wu, Wenxi Liu, Wenzhong Guo, Rynson W. H. Lau
To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images.
no code implementations • ICLR 2021 • Nanxuan Zhao, Zhirong Wu, Rynson W. H. Lau, Stephen Lin
Contrastive visual pretraining based on the instance discrimination pretext task has made significant progress.
no code implementations • 14 Apr 2020 • Nanxuan Zhao, Zhirong Wu, Rynson W. H. Lau, Stephen Lin
To address this problem, we propose a data-driven approach for learning invariance to backgrounds.
no code implementations • 15 Mar 2020 • Xin Tan, Ke Xu, Ying Cao, Yiheng Zhang, Lizhuang Ma, Rynson W. H. Lau
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.
2 code implementations • ICCV 2019 • Zhanghan Ke, Daoye Wang, Qiong Yan, Jimmy Ren, Rynson W. H. Lau
In this work, we show that the coupled EMA teacher causes a performance bottleneck.
Semi-Supervised Image Classification Unsupervised Domain Adaptation
1 code implementation • ICCV 2019 • Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Bao-Cai Yin, Rynson W. H. Lau
To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach.
no code implementations • 27 Sep 2018 • Wenxi Liu, Yibing Song, Dengsheng Chen, Shengfeng He, Yuanlong Yu, Tao Yan, Gerhard P. Hancke, Rynson W. H. Lau
In addition, we also propose a gated fusion scheme to control how the variations captured by the deformable convolution affect the original appearance.
no code implementations • ECCV 2018 • Quanlong Zheng, Jianbo Jiao, Ying Cao, Rynson W. H. Lau
Inspired by the observation that given a specific task, human attention is strongly correlated with certain semantic components on a webpage (e. g., images, buttons and input boxes), our network explicitly disentangles saliency prediction into two independent sub-tasks: task-specific attention shift prediction and task-free saliency prediction.
1 code implementation • CVPR 2018 • Jiawei Zhang, Jinshan Pan, Jimmy Ren, Yibing Song, Linchao Bao, Rynson W. H. Lau, Ming-Hsuan Yang
The proposed network is composed of three deep convolutional neural networks (CNNs) and a recurrent neural network (RNN).
Ranked #10 on Deblurring on RealBlur-R (trained on GoPro) (SSIM (sRGB) metric)
no code implementations • 10 Nov 2017 • Shao Huang, Weiqiang Wang, Shengfeng He, Rynson W. H. Lau
Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years.
no code implementations • ICCV 2017 • Shengfeng He, Jianbo Jiao, Xiaodan Zhang, Guoqiang Han, Rynson W. H. Lau
Experiments show that the proposed multi-task network outperforms existing multi-task architectures, and the auxiliary subitizing network provides strong guidance to salient object detection by reducing false positives and producing coherent saliency maps.
3 code implementations • CVPR 2017 • Liangqiong Qu, Jiandong Tian, Shengfeng He, Yandong Tang, Rynson W. H. Lau
Two levels of features are derived from the global network and transferred to two parallel networks.
no code implementations • CVPR 2016 • Shengfeng He, Rynson W. H. Lau, Qingxiong Yang
To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects.
no code implementations • 31 Mar 2016 • Wenxi Liu, Rynson W. H. Lau, Xiaogang Wang, Dinesh Manocha
Specifically, we propose an optimization framework that filters out the unknown noise in the crowd trajectories and measures their similarity to the exemplar-AMMs to produce a crowd motion feature.
no code implementations • ICCV 2015 • Shengfeng He, Rynson W. H. Lau
In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object.
no code implementations • 10 Feb 2014 • Wenxi Liu, Antoni B. Chan, Rynson W. H. Lau, Dinesh Manocha
We present a multiple-person tracking algorithm, based on combining particle filters and RVO, an agent-based crowd model that infers collision-free velocities so as to predict pedestrian's motion.
no code implementations • Video, Image, and Sound Analysis Lab (VISAL) at the City University of Hong Kong! 2014 • Xufang Pang, Ying Cao, Rynson W. H. Lau, and Antoni B. Chan
Automatically extracting frames/panels from digital comic pages is crucial for techniques that facilitate comic reading on mobile devices with limited display areas.
no code implementations • CVPR 2013 • Shengfeng He, Qingxiong Yang, Rynson W. H. Lau, Jiang Wang, Ming-Hsuan Yang
A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in realtime even with hundreds of regions.