圆形图片

Ke XU

许 可

Research Fellow

City University of Hong Kong

Email: kkangwing at gmail dot com

Biography


I currently work at the City University of Hong Kong. I obtained a dual PhD in Computer Science from Dalian University of Technology and City University of Hong Kong in 2021. My research interest lies at the intersection of computer vision, computer graphics, and machine learning, where I explore advanced AI techniques to facilitate computers to see, understand, and recreate the richness of content in everyday and professional activities. My work addresses challenges of capture and learning, including imaging and building effective representations under harsh conditions (e.g., low and/or high illumination, rain, and sparse capture rigs) at varying time/scene/data scales. My research papers generally appear in premier venues featuring computer vision, graphics, and machine learning (e.g., CVPR/SIGGRAPH (Asia)/NeurIPS).


Service/Award


Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI, SIGGRAPH (Asia)

Journal Reviewer: IJCV, TPAMI, TIP

CVPR Outstanding Reviewer 2025

IJCV Outstanding Reviewer Award 2024

BMVC Best Student Paper Runner-Up Award 2020

NeurIPS Top Reviewer 2019


Selected Publications  [Google Scholar] [DBLP] [ORCID] [OpenReview]


HRC-Net Teaser
HRC-Net: Learning Visual Hypothesis, Representative, and Collaboration for Multi-Domain Image Inpainting
Xin Wang, Di Lin, Wanchao Su, Ji Du, Renjie Zhang, Jie Zhang, Haotian Dong, Ke Xu, Qing Guo, Ping Li
ACM Trans. on Graphics (Proc. ACM SIGGRAPH Asia, conditionally accepted), Dec. 2025
[Paper|Code]
StyleSculptor Teaser
StyleSculptor: Zero-Shot Stylized 3D Asset Generation with Texture-Geometry Dual Guidance
Zefan Qu, Zhenwei Wang, Haoyuan Wang, Ke Xu, Gerhard Hancke, Rynson Lau
Proc. ACM SIGGRAPH Asia (conditionally accepted), Dec. 2025
[Paper|Code]
SEHDR Teaser
SEHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing
Yiyu Li, Haoyuan Wang, Ke Xu, Gerhard Hancke, Rynson Lau
Proc. IEEE ICCV, Oct. 2025
[Paper|Code]
4DGV Teaser
4D Gaussian Video with Motion Layering
Pinxuan Dai, Peiquan Zhang, Zheng Dong, Ke Xu, Yifan Peng, Dandan Ding, Yujun Shen, Yin Yang, Xinguo Liu, Rynson Lau, Weiwei Xu
ACM Trans. on Graphics (Proc. ACM SIGGRAPH), Aug. 2025
[Paper|Code]
LGSOR Teaser
Language-Guided Salient Object Ranking
Fang Liu, Yuhao Liu, Ke Xu, Shuquan Ye, Gerhard Hancke, Rynson Lau
Proc. IEEE CVPR, June 2025
[Paper|Code]
GhostingNet Teaser
GhostingNet: a Novel Approach for Glass Surface Detection with Ghosting Cues
Tao Yan, Jiahui Gao, Ke Xu, Xiangjie Zhu, Hao Huang, Helong Li, Benjamin Wah, Rynson Lau
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2025
[Paper|Code]
StereoDerain Teaser
APANet: Asymmetrical Parallax Attention Network For Efficient Stereo Image Deraining
Chenglong Wang, Tao Yan, Weilong Huang, Xianglong Chen, Ke Xu, Xiaojun Chang
IEEE Trans. on Computational Imaging (TCI), 2025
[Paper|Code]
LushNeRF Teaser
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Zefan Qu, Ke Xu*, Gerhard Hancke, Rynson Lau
Proc. NeurIPS, Dec. 2024
[Paper|Code]
GSP Teaser
Gaussian Surfel Splatting for Live Human Performance Capture
Zheng Dong, Ke Xu, Yaoan Gao, Hujun Bao, Weiwei Xu, Rynson Lau
ACM Trans. on Graphics (Proc. ACM SIGGRAPH Asia), Dec. 2024
[Paper|Code|Video1|Video2]
USID Teaser
Unsupervised Salient Instance Detection
Xin Tian, Ke Xu*, Rynson Lau
Proc. IEEE CVPR, June 2024
[Paper]
CSEC Teaser
Color Shift Estimation-and-Correction for Image Enhancement
Yiyu Li, Ke Xu, Gerhard Hancke, Rynson Lau
Proc. IEEE CVPR, June 2024
[Paper|Project]
MGVMD Teaser
Effective Video Mirror Detection with Inconsistent Motion Cues
Alex Warren, Ke Xu, Jiaying Lin, Garry Tam, Rynson Lau
Proc. IEEE CVPR, June 2024
[Paper|Project|Video]
shadow Teaser
Recasting Regional Lighting for Shadow Removal
Yuhao Liu, Zhanghan Ke, Ke Xu*, Fang Liu, Zhenwei Wang, Rynson Lau
Proc. AAAI (Oral), Feb. 2024
[Paper|Dataset&Results]
MVVGD Teaser
Multi-view Reflection Dynamics for Video Glass Surface Detection
Fang Liu, Yuhao Liu, Jiaying Lin, Ke Xu*, Rynson Lau
Proc. AAAI, Feb. 2024
[Paper|Code]
ZOOM Teaser
ZOOM: Learning Video Mirror Detection With Extremely-Weak Supervision
Ke Xu*, Tsun Wai Siu*, Rynson Lau
Proc. AAAI, Feb. 2024
[Paper|Dataset]
SAILOR Teaser
SAILOR: Synergizing Radiance and Occupancy Fields for Live Human Performance Capture
Zheng Dong, Ke Xu, Yaoan Gao, Qilin Sun, Hujun Bao, Weiwei Xu, Rynson Lau
ACM Trans. on Graphics (Proc. ACM SIGGRAPH Asia), Dec. 2023
[Paper|Project]
LLNeRF Teaser
Lighting up NeRF via Unsupervised Decomposition and Enhancement
Haoyuan Wang, Xiaogang Xu, Ke Xu*, Rynson Lau
Proc. IEEE ICCV, Oct. 2023
[Paper|Project]
AIM Teaser
Adaptive Illumination Mapping for Shadow Detection in Raw Images
Jiayu Sun*, Ke Xu*, Youwei Pang, Lihe Zhang, Huchuan Lu, Gerhard Hancke, Rynson Lau
Proc. IEEE ICCV, Oct. 2023
[Paper|Project]
Harmonizer Teaser
Learning Image Harmonization in the Linear Color Space
Ke Xu, Gerhard Hancke, Rynson Lau
Proc. IEEE ICCV, Oct. 2023
[Paper|Project]
WRIS Teaser
Referring Image Segmentation Using Text Supervision
Fang Liu, Yuhao Liu, Yuqiu Kong, Ke Xu*, Lihe Zhang, Baocai Yin, Gerhard Hancke, Rynson Lau
Proc. IEEE ICCV, Oct. 2023
[Paper|Project]
OPNet Teaser
Camouflaged Object Segmentation with Omni Perception
Haiyang Mei, Ke Xu, Yunduo Zhou, Yang Wang, Haiyin Piao, Xiaopeng Wei, Xin Yang
International Journal of Computer Vision (IJCV), 2023
[Paper|Code]
Structure Teaser
Structure-Informed Shadow Removal Networks
Yuhao Liu, Qing Guo, Lan Fu, Zhanghan Ke, Ke Xu, Wei Feng, Ivor Tsang, Rynson Lau
IEEE Trans. on Image Processing (TIP), 2023
[Paper]
>
Boosting Teaser
Boosting Night-time Scene Parsing with Learnable Frequency
Zhifeng Xie, Sen Wang, Ke Xu, Zhizhong Zhang, Xin Tan, Yuan Xie, Lizhuang Ma
IEEE Trans. on Image Processing (TIP), 2023
[Paper|Code]
GTPIFU Teaser
Geometry-aware Two-scale PIFu Representation for Human Reconstruction
Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson Lau
Proc. NeurIPS (Spotlight), Nov. 2022
[Paper|Project]
Matting Teaser
Semantics-Adding Flaw-Erasing Network for Semantic Human Matting
Jiayu Sun, Zhanghan Ke, Ke Xu, Guofeng Zhang, Lihe Zhang, Huchuan Lu, Rynson Lau
Proc. BMVC (Oral), Nov. 2022
[Paper|Code]
lightfield Teaser
Weakly-Supervised Salient Object Detection on Light Fields
Zijian Liang, Pengjie Wang, Ke Xu, Pingping Zhang, Rynson Lau
IEEE Trans. on Image Processing (TIP), 2022
[Paper]
Harmonizer Teaser
Harmonizer: Learning to Perform White-Box Image and Video Harmonization
Zhanghan Ke, Chunyi Sun, Lei Zhu, Ke Xu, Rynson Lau
Proc. ECCV, Oct. 2022
[Paper|Code|Youtube Demo 1|Demo 2]
LCDP Teaser
Local Color Distributions Prior for Image Enhancement
Haoyuan Wang, Ke Xu*, Rynson Lau
Proc. ECCV, Oct. 2022
[Paper|Project]
VCNet Teaser
Mirror Detection with the Visual Chirality Cue
Xin Tan, Jiaying Lin, Ke Xu*, Pan Chen, Lizhuang Ma, Rynson Lau
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2022
[Paper|Code]
OCOR Teaser
Bi-directional Object-context Prioritization Learning for Saliency Ranking
Xin Tian, Ke Xu*, Xin Yang, Lin Du, Baocai Yin, Rynson Lau
Proc. IEEE CVPR, June 2022
[Paper|Code]
Curve Teaser
Rethinking Efficient Lane Detection via Curve Modeling
Zhengyang Feng, Shaohua Guo, Xin Tan, Ke Xu*, Min Wang, Lizhuang Ma
Proc. IEEE CVPR, June 2022
[Paper|Project]
ISDNet Teaser
ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-high Resolution Segmentation
Shaohua Guo, Liang Liu, Zhenye Gan, Yabiao Wang, Wuhao Zhang, Chengjie Wang,
Guannan Jiang, Wei Zhang, Ran Yi, Lizhuang Ma, Ke Xu
Proc. IEEE CVPR, June 2022
[Paper|Code]
SID Teaser
Learning to Detect Instance-level Salient Objects Using Complementary Image Labels
Xin Tian*, Ke Xu*, Xin Yang, Baocai Yin, Rynson Lau
International Journal of Computer Vision (IJCV), 2022
[Paper|Code]
nightCity Teaser
Night-time Scene Parsing with a Large Real Dataset
Xin Tan, Ke Xu*, Ying Cao, Yiheng Zhang, Lizhuang Ma, Rynson Lau
IEEE Trans. on Image Processing (TIP), 2021
[Paper|Project]
>
Deraining Teaser
Intensity-Aware Single-Image Deraining with Semantic and Color Regularization
Ke Xu, Xin Tian, Xin Yang, Baocai Yin, Rynson Lau
IEEE Trans. on Image Processing (TIP), 2021
[Paper|Code]
FDRNet Teaser
Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting
Lei Zhu, Ke Xu*, Zhanghan Ke, Rynson Lau
Proc. IEEE ICCV, Oct. 2021
[Paper|Code]
LARR Teaser
Location-aware Single Image Reflection Removal
Zheng Dong, Ke Xu, Yin Yang, Hujun Bao, Weiwei Xu, Rynson Lau
Proc. IEEE ICCV, Oct. 2021
[Paper|Project]
WSSID Teaser
Weakly-Supervised Salient Instance Detection
Xin Tian, Ke Xu, Xin Yang, Baocai Yin, Rynson Lau
Proc. BMVC (Best Student Paper Runner-Up), Sept. 2020
[Paper|Code]
Lowlight Teaser
Learning to Restore Low-Light Images via Decomposition-and-Enhancement
Ke Xu, Xin Yang, Baocai Yin, Rynson Lau
Proc. IEEE CVPR, June 2020
[Paper|Code|Dataset]
mirrorNet Teaser
Where is My Mirror?
Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Baocai Yin, Rynson Lau
Proc. IEEE ICCV, Oct. 2019
[Paper|Project]
SPANet Teaser
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
Tianyu Wang, Xin Yang, Ke Xu, Shaozhe Chen, Qiang Zhang, Rynson Lau
Proc. IEEE CVPR, June 2019
[Paper|Code|Dataset]
Active Matting Teaser
Active Matting
Xin Yang*, Ke Xu*, Shaozhe Chen, Shengfeng He, Baocai Yin, Rynson Lau
Proc. NeurIPS, Dec. 2018
[Paper|Code|Dataset]
DRHT Teaser
Image Correction via Deep Reciprocating HDR Transformation
Xin Yang*, Ke Xu*, Yibing Song, Qiang Zhang, Xiaopeng Wei, Rynson Lau (* joint first authors)
Proc. IEEE CVPR, June 2018
[Paper|Code|Dataset]