LI XU

CEO, SenseTime Group Limited


Email: xuli@sensetime.com

RECENT GOAL:

We aim at using computer vision technologies to change the world. If you happen to think the same, join us.


PUBLICATIONS:

Google Scholar

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

[project][paper]

Xiaoyong Shen, Chao Zhou, Li Xu, Jiaya Jia, "Mutual-Structure for Joint Filtering" International Conference on Computer Vision (ICCV), (oral presentation), 2015.

[project][paper][code]

Jianping Shi, Qiong Yan, Li Xu, Jiaya Jia, "Hierarchical Image Saliency Detection on Extended CSSD" IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.

[project][paper]

Jianping Shi, Xin Tao, Li Xu, Jiaya Jia, "Break Ames Room Illusion: Depth from General Single Images" ACM Transactions on Graphics (TOG), (Proc. ACM SIGGRAPH ASIA 2015).

[paper]

Yongtao Hu, Jimmy SJ. Ren, Jingwen Dai, Chang Yuan, Li Xu, Wenping Wang, "Deep Multimodal Speaker Naming" ACM International Conference on Multimedia (MM), 2015.

[project][paper][video]

Li Xu, Jimmy SJ. Ren, Qiong Yan, Renjie Liao, Jiaya Jia "Deep Edge-Aware Filters" International Conference on Machine Learning (ICML), 2015.

[project][paper][code]

Jianping Shi, Li Xu, Jiaya Jia "Just Noticeable Defocus Blur Detection and Estimation" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.

[project][paper]

Ziyang Ma, Renjie Liao, Xin Tao, Li Xu, Jiaya Jia, Enhua Wu "Handling Motion Blur in Multi-Frame Super-Resolution" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.

[paper]

Xiaoyong Shen, Qiong Yan, Li Xu, Lizhuang Ma, Jiaya Jia"Multispectral Joint Image Restoration via Optimizing a Scale Map" IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015.

[paper]

Jimmy SJ. Ren, Li Xu, "On Vectorization of Deep Convolutional Neural Networks for Vision Tasks" AAAI Conference on Artificial Intelligence (AAAI), 2015.

[project][paper]

Li Xu, Jimmy SJ. Ren, Ce Liu, Jiaya Jia, "Deep Convolutional Neural Network for Image Deconvolution" Advances in Neural Information Processing Systems (NIPS), 2014.

[project][paper]

Li Xu, Xin Tao, Jiaya Jia, "Inverse Kernels for Fast Spatial Deconvolution" European Conference on Computer Vision (ECCV), 2014.

[paper][video]

Xiaoyong Shen, Li Xu, Qi Zhang, Jiaya Jia, "Multi-Modal and Multi-Spectral Registration for Natural Images" European Conference on Computer Vision (ECCV), 2014.

[paper]

Qi Zhang, Xiaoyong Shen, Li Xu, Jiaya Jia, "Rolling Guidance Filter" European Conference on Computer Vision (ECCV) (oral presentation), 2014.

[project][paper]

Cewu Lu, Li Xu, Jiaya Jia, "Contrast Preserving Decolorization with Perception-Based Quality Metrics" International Journal of Computer Vision (IJCV), 2014.

[paper]

Qi Zhang, Li Xu, Jiaya Jia, "100+ Times Faster Weighted Median Filter (WMF)" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

[project][paper]

Zhe Hu, Li Xu, Ming-Hsuan Yang, "Joint Depth Estimation and Camera Shake Removal from Single Blurry Image" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

[project][paper]

Jianping Shi, Li Xu, Jiaya Jia, "Discriminative Blur Detection Features" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

[project][paper]

Li Xu, Qiong Yan, Jiaya Jia, "A Sparse Control Model for Image and Video Editing" ACM Transactions on Graphics (TOG), 32(6): 197 (Proc. ACM SIGGRAPH ASIA 2013).

[project][paper]

Qiong Yan, Li Xu , Jiaya Jia, "Dense Scattering Media Removal" ACM SIGGRAPH ASIA 2013, Technical Briefs, 2013.

[paper][full technical report][ software]

Shicheng Zheng, Li Xu , Jiaya Jia, "Forward Motion Deblurring" IEEE International Conference on Computer Vision (ICCV), 2013.

[project][paper]

Qiong Yan, Xiaoyong Shen, Li Xu, Shaojie Zhuo, Xiaopeng Zhang, Liang Shen, Jiaya Jia, "Cross-Field Joint Image Restoration vis Scale Map" IEEE International Conference on Computer Vision (ICCV), 2013.

[project][paper][supplementary material]

Li Xu, Shicheng Zheng, Jiaya Jia, "Unnatural L0 Sparse Representation for Natural Image Deblurring", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

[project][paper][supplementary material]

Qinog Yan, Li Xu, Jianping Shi, Jiaya Jia, "Hierarchical Saliency Detection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

[project][paper][supplementary material][dataset]

Li Xu, Qiong Yan, Yang Xia, Jiaya Jia, "Structure Extraction from Texture via Relative Total Variation", ACM Transactions on Graphics (TOG), 31(6), 139, (Proc. ACM SIGGRAPH ASIA 2012), 2012.

[project][paper][matlab code]

Cewu Lu, Li Xu, Jiaya Jia, "Real-time Contrast Preserving Decolorization", ACM SIGGRAPH ASIA 2012 Technical Briefs, 2012.

[paper][matlab code]

Chun-Ho Hung, Li Xu, Jiaya Jia, "Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles", International Journal of Computer Vision (IJCV), 102(1-3), 271-292, 2013.

[project][paper][video]

Li Xu, Zhenlong Dai, Jiaya Jia, "Scale Invariant Optical Flow", European Conference on Computer Vision (ECCV), 2012.

[project][paper]

Cewu Lu, Li Xu, Jiaya Jia, "Combining Sketch and Tone for Pencil Drawing Production", International Symposium on Non-Photorealistic Animation and Rendering (NPAR), 2012. (Best Paper Award)

[project][paper][slides]

Li Xu, Jiaya Jia, "Depth-Aware Motion Deblurring", IEEE International Conference on Computational Photography (ICCP), 2012.

[project][paper]

Cewu Lu, Li Xu, Jiaya Jia, "Contrast Preserving Decolorization", IEEE International Conference on Computational Photography (ICCP), 2012.(The method has been included in OpenCV 3.0 decolor)

[project][paper][matlab code]

Li Xu, Cewu Lu, Yi Xu, Jiaya Jia, "Image Smoothing via L0 Gradient Minimization", ACM Transactions on Graphics (TOG), 30(6), 174, (Proc. ACM SIGGRAPH ASIA 2011), 2011. (The most cited paper in Proc. ACM SIGGRAPH ASIA 2011)

[project][paper][video]
[software (GPU enabled)][matlab code][edge adjustment tool]

Li Xu, Jiaya Jia, Yasuyuki Matsushita,"Motion Detail Preserving Optical Flow Estimation", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(9), 1744-1757, 2012.

[project][paper][software]

Li Xu, Jiaya Jia, Sing Bing Kang, "Improving Sub-pixel Correspondence through Upsampling", Computer Vision and Image Understanding (CVIU), 116(2), 250-261, 2012.

[paper]

Li Xu, Jiaya Jia, "Two-Phase Kernel Estimation for Robust Motion Deblurring", European Conference on Computer Vision (ECCV), 2010.(The 5th most cited paper in Proc. ECCV 2010)

[project][paper][supplementary material][video]
[software (GPU enabled)][blind deconvolution][non-blind deconvolution]

Li Xu, Jiaya Jia, Yasuyuki Matsushita, "Motion Detail Preserving Optical Flow Estimation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. (oral presentation, AR: 78/1724 ~4.5%)

[project][paper][technical report][software]

Li Xu, Jianing Chen, and Jiaya Jia, "A Segmentation Based Variational Model for Accurate Optical Flow Estimation", European Conference on Computer Vision (ECCV), 2008.

[paper][video][software]

Li Xu and Jiaya Jia, "Stereo Matching: An Outlier Confidence Approach", European Conference on Computer Vision (ECCV), 2008.

[paper]

Li Xu, Takayoshi Yamashita, Shihong Lao, Masato Kawade, Feihu Qi,"Online Real Boosting for Object Tracking under Severe Apprearance Changes and Occlusion", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2007.

[paper][video][software]

Li Xu, Feihu Qi, Renjie Jiang, "Shadow Removal from a Single Image", International Conference on Intelligent System Design and Applications (ISDA), 2006.

[paper]

Renjie Jiang, Feihu Qi, Li Xu, Guorong Wu, "Detecting and segmenting text from natural scenes with 2-stage classification", International Conference on Intelligent System Design and Applications (ISDA), 2006.

[paper][software]



RESEARCH:

My research interests lie in the areas of computer vision and computational photography. I am pretty much interested in building practical vision systems. Most of my research work has software and source code publicly available. My representative work includes optical flow (MDP-Flow2), motion deblurring (Robust Motion Deblurring), image/video representation (L0 Smoothing). I am recently interested in the combination of deep neural network and conventional generative vision models.


HONORS & AWARDS:

Best Reviewer, ICCV 2015

Best Reviewer, ACCV 2012

Best Paper Award, NPAR 2012

Best Teaching Assistant Certificate of Merit Award, 2009-2010

Booz & Company Social Venture Challenge Finalist (team leader), 2009

Microsoft Research Asia Fellowship Award, 2008

Award for Exemption of National Graduate Entry Examinations

Exceptional Student of SJTU (top 10% in Dept. of CSE), 2001, 2003


RESEARCH EXPERIENCES:

2013.3 Microsoft Research New England (Boston)

Work with Ce Liu


2008.6~2008.9 Microsoft Research Asia (Beijing)

Visual Computing

Work with Yasuyuki Matsushita


2006.6~2006.10 OMRON Keihanna Innovation Centre (Kyoto, Japan)

Sensing & Control Technology Laboratory/OKAO Vision

Work with Takayoshi Yamashita, Shihong Lao


2004.10~2006.4 Motorola China Research Centre (Shanghai)

Pattern Recognition Group

Work with Qingshan Chen


PROFESSIONAL ACTIVITIES:

Journal Reviewer

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal on Computer Vision (IJCV)
IEEE Transactions on Image Processing (TIP)
Transaction on Graphics (TOG)
Computer Vision and Image Understanding (CVIU)
The Visual Computer

Conference Reviewer/External Reviewer

CVPR 2010-2015, ECCV 2010-2014
ICCV 2011-2015, Best Reviewer, ICCV 2015
Program Committee: CVPR 2013, ACCV 2012, 2014, Best Reviewer, ACCV 2014, Industry Co-Chair ACCV 2016
SIGGRAPH ASIA 2011-2015; SIGGRAPH 2012-2015