Biography

I received the Ph.D. degree from the Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST) in 2014, and B.Eng. degree from the School of Electronic & Electrical Engineering, Nanjing University in 2009. During my Ph.D. study from Sep. 2009 to Mar. 2014, I was supervised by Prof. Oscar C. Au. From Sep. to Dec. 2012, I visited National Institute of Informatics (NII) as a research intern under the supervision of Prof. Gene Cheung.

I’m interested in large language models and computer vision. In particular, I worked on depth sensing, segmentation, and image processing to solve real-world problems. Currently, I’m focusing on LLM evaluation and development to advance the progress of the next AGI.

I am currently working at SenseTime as a Research Director and recruiting self-motivated researchers and engineers who is eager and patient to make contributions to the world. If interested, please drop your CV to my email.

News

• We are hosting an ECCV 2022 workshop, details will be available soon!
• 2 papers accepted to ICCV 2021
• 2 papers accepted to CVPR 2021
• 1 paper accepted to ICLR 2021
• 1 paper accepted to TPAMI 2020
• 2 papers accepted to ECCV 2020
• No. 1 in ECCV AIM 2020 Video Interpolation Challenge
• 1 paper accepted to TIP 2020
• 1 paper accepted to ICML 2020
• 2 papers accepted to CVPR 202020
• No. 1 in ICCV AIM 2019 Video Interpolation Challenge
• 1 paper accepted as spotlight to NeurIPS 2019
• 2 papers accepted to ICCV 2019
• 3 papers accepted to CVPR 2019
  

Selected Publications

Dual-Camera Super-Resolution with Aligned Attention Modules
Tengfei Wang, Jiaxin Xie, Wenxiu Sun, Qiong Yan, Qifeng Chen
International Conference on Computer Vision,  (ICCV 2021) – Oral
[code]

FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, Jifeng Dai, Hongsheng Li
International Conference on Computer Vision,  (ICCV 2021)
[code]

Deep Animation Video Interpolation in the Wild
Li Siyao, Shiyu Zhao, Weijiang Yu, Wenxiu Sun, Dimitris Metaxas, Chen Change Loy, Ziwei Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021)
[code]

Efficient Regional Memory Network for Video Object Segmentation
Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021)
[code]

Semi-synthesis: A fast way to produce effective datasets for stereo matching
Ju He, Enyu Zhou, Liusheng Sun, Fei Lei, Chenyang Liu, Wenxiu Sun
IEEE Conference on Computer Vision and Pattern Recognition – Workshop (CVPRW 2021)

Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, Hongsheng Li
International Conference on Learning Representations (ICLR 2021)
[open review] [presentation]

Exploiting Raw Images for Real-Scene Super-Resolution
Xiangyu Xu, Yongrui Ma, Wenxiu Sun, Ming-Hsuan Yang
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI, 2020)

GRNet: Gridding Residual Network for Dense Point Cloud Completion
Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, Wenxiu Sun
European Conference on Computer Vision,  (ECCV 2020)
[code]

Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention
Quewei Li, Jie Guo, Yang Fei, Qinyu Tang, Wenxiu Sun, Jin Zeng, Yanwen Guo
European Conference on Computer Vision,  (ECCV 2020)

Enhanced Quadratic Video Interpolation
Yihao Liu, Liangbin Xie, Li Siyao, Wenxiu Sun, Yu Qiao, Chao Dong
European Conference on Computer Vision – AIM2020 Workshop,  (ECCV 2020)
No. 1 in AIM2020 VTSR Challenge
[code]

Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
Xiangyu Xu, Muchen Li, Wenxiu Sun, Ming-Hsuan Yang
IEEE Transactions on Image Processing, VOL. 29, 2020,  (TIP 2020)

Learning Factorized Weight Matrix for Joint Filtering
Xiangyu Xu, Yongrui Ma, Wenxiu Sun
Proceedings of the 37th International Conference on Machine Learning,  (ICML 2020)

Pix2Vox++: multi-scale context-aware 3D object reconstruction from single and multiple images
Haozhe Xie, Hongxun Yao, Shengping Zhang, Shangchen Zhou, Wenxiu Sun
International Journal of Computer Vision (IJCV2020)
[code]

Towards Geometry Guided Neural Relighting with Flash Photography
Di Qiu, Jin Zeng, Zhanghan Ke, Wenxiu Sun, Chengxi Yang
International Conference on 3D Vision (3DV 2020)

StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
Rui Liu, Chengxi Yang, Wenxiu Sun, Xiaogang Wang, Hongsheng Li
Advances in Neural Information Processing Systems (CVPR 2020)

Polarized Reflection Removal with Perfect Alignment in the Wild
Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan, Wenxiu Sun, Qifeng Chen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020)
[code]

Quadratic Video Interpolation
Xiangyu Xu, Li Si-Yao, Wenxiu Sun, Qian Yin, Ming-Hsuan Yang
Advances in Neural Information Processing Systems (NeurIPS 2019) – Spotlight

Quadratic Video Interpolation for VTSR Challenge
Li Si-Yao, Ze Pan, Xiangyu Xu, Wenxiu Sun
International Conference on Computer Vision – Workshop on Advances in Image Manipulation (ICCVW 2019)
No. 1 in ICCV AIM 2019 Video Interpolation Challenge

Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module
Di Qiu, Jiahao Pang, Wenxiu Sun, and Chengxi Yang
International Conference on Computer Vision (ICCV 2019)
[code]

Towards Real Scene Super-Resolution with Raw Images
Xiangyu Xu, Yongrui Ma, and Wenxiu Sun
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)

Deep Surface Normal Estimation with Hierarchical RGB-D Fusion
Jin Zeng, Yanfeng Tong, Yunmu Huang, Qiong Yan, Wenxiu Sun, Jing Chen, and Yongtian Wan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019)
[code]

Learning Deformable Kernels for Image and Video Denoising
Xiangyu Xu, Muchen Li, and Wenxiu Sun
arXiv preprint arXiv:1904.06903 (2019).

DSR: Direct Self-rectification for Uncalibrated Dual-lens Cameras
Ruichao Xiao, Wenxiu Sun, Jiahao Pang, Qiong Yan, and Jimmy Ren
International Conference on 3D Vision (3DV 2018)
[code]

Deep graph Laplacian regularization for robust denoising of real images
Jin Zeng, Jiahao Pang, Wenxiu Sun, and Gene Cheung
IEEE Conference on Computer Vision and Pattern Recognition – Workshop (CVPRW 2019)

Convolutional Memory Blocks for Depth Data Representation Learning
Keze Wang, Liang Lin, Chuangjie Ren, Wei Zhang, and Wenxiu Sun
The 27th International Joint Conference on Artificial Intelligence (IJCAI 2018)

Monocular depth estimation with affinity, vertical pooling, and label enhancement
Yukang Gan, Xiangyu Xu, Wenxiu Sun, and Liang Lin
European Conference on Computer Vision (ECCV 2018)

Zoom and learn: Generalizing deep stereo matching to novel domains
Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, and Liang Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018)

Cascade residual learning: A two-stage convolutional neural network for stereo matching
Jiahao Pang, Wenxiu Sun, Jimmy SJ Ren, Chengxi Yang, and Qiong Yan
International Conference on Computer Vision (ICCV 2017)
No. 1 in KITTI2015 from Mar 2016 – Sep 2016
[code]

Single View Stereo Matching
Yue Luo, Jimmy S. Ren, Mude Lin, Jiahao Pang, Wenxiu Sun, Hongsheng Li, Liang Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018) – spotlight.

LSTM Pose Machines
Yue Luo, Jimmy S. Ren, Zhouxia Wang, Wenxiu Sun, Jinshan Pan, Jianbo Liu, Jiahao Pang, Liang Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018).
[code]

Accurate Single Stage Detector Using Recurrent Rolling Convolution
Jimmy S. Ren, Xiaohao Chen, Jianbo Liu, Wenxiu Sun, Jiahao Pang, Qiong Yan, Yu-Wing Tai, Li Xu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

Look, Listen and Learn – A Multimodal LSTM for Speaker Identification
Jimmy S. Ren, Yongtao Hu, Yu-Wing Tai, Chuan Wang, Li Xu, Wenxiu Sun, Qiong Yan
The 30th AAAI Conference on Artificial Intelligence (AAAI 2016) – oral

Shepard Convolutional Neural Networks
Jimmy S. Ren, Li Xu, Qiong Yan, Wenxiu Sun
Advances in Neural Information Processing Systems (NeurIPS 2015)

Seamless View Synthesis through Texture Optimization
Wenxiu Sun, Oscar C. Au, Lingfeng Xu, Yujun Li, Wei Hu
IEEE Trans. Image Processing, vol 23, no. 1, 2014. (TIP 2014)

Awards

• SenseTime Award, 2019
• No. 1 in AIM 2020 Video Interpolation Challenge
• No. 1 in AIM 2019 Video Interpolation Challenge
• No. 1 in KITTI2015 from Mar 2016 – Sep 2016

UPDATED ON Oct 08, 2024