Chen Li
I am currently a senior researcher in Tencent Youtu X-Lab and work with Dr. Jiaya jia and Dr. Yu-wing Tai. Before I joined Tencent in Spet. 2017, I worked as an algorithm engineer in Dajiang Innovation for eight months.

I got my Ph.D. degree, under the supervision of Prof.Kun Zhou, and the B.Eng degree from Zhejiang University in 2017 and 2011, respectively. During Feb. 2012 to Dec. 2016, I worked with Dr. Steve Lin in Mcrosoft Research, Beijing, as an research intern.
Email  /  CV  /  LinkedIn
  Research Interests My current research interests fall in the field of computer vision and computer graphics, specifically the 3D reconstruction, appearance modeling, computational photography, and the relevant VR/AR applications on facial images.
I believe the human face is one of the most important and interesting reserach objects in both CV and CG.
  Professional Activities Reviewer, Pacific Graphics 2015, 2017
Reviewer, CVPR 2018
Reviewer, IEEE TIP, TVCG, TPAMI
  Journals Physically-Based Simulation of Cosmetics via Intrinsic Image Decomposition with Facial Priors Chen Li, Kun Zhou, Hsiang-Tao Wu, Stephen Lin IEEE Transactions ON Pattern Analysis and Machine Intelligence (TPAMI), vol.40, 2018 [Preprint] [Bibtex] [Video] This paper combines our ECCV2014 and CVPR2015 work with extensions on cosmetics with spatial-varying reflectance and video inputs. Face Inpainting based on High-Level Facial Attributes MahdiJampour, Chen Li, Lap-Fai Yu, Kun Zhou, Stephen Lin, Horst Bischof Computer Vision and Image Understanding (CVIU), 2017 [Supplementary Material] [Video] [Bibtex] Combining high-level and low-level cues for inpainting occluded face images. Bayesian Depth-from-Defocus with Shading Constraints Chen Li, Shuochen Su, Yasuyuki Matsushita, Kun Zhou, Stephen Lin IEEE Transactions ON Image Processing (TIP), vol.25, no.2, pp.589-600, Feb. 2016 [Preprint] [Bibtex] This paper extends our CVPR2013 work including a new optimization, an approach for handling uncalibrated images and results for natural images.   Conferences Radiometric Calibration from Faces in Images Chen Li, Stephen Lin, Kun Zhou, Katsushi Ikeuchi IEEE Computer Vision and Pattern Recognition (CVPR), 2017 [Paper] [Supplementary Material] [Poster] [Bibtex] A radiometric calibration method based on a low-rank property that exists among certain skin albedo gradients because of the pigments within the skin. This use of human face data may complement existing approaches that operate on other scene areas. Specular Highlight Removal in Facial Images Chen Li, Stephen Lin, Kun Zhou, Katsushi Ikeuchi IEEE Computer Vision and Pattern Recognition (CVPR), 2017 [Paper] [Supplementary Material] [Poster] [Bibtex] A method for removing specular highlight reflections in facial images that may contain varying illumination colors which demonstrates appreciable improvements over previous state-of-art methods, especially for handling partially saturated pixels, varying illumination colors, and ambiguities caused by the similarity between illumination chromaticity and diffuse chromaticity. Simulating Makeup through Physics-based Manipulation of Intrinsic Image Layers Chen Li, Kun Zhou, Stephen Lin IEEE Computer Vision and Pattern Recognition (CVPR), 2015 [Paper] [Extended Abstract] [Poster] [Bibtex] A realistic simulation of the different effects of cosmetics including foundation, blush, lipstick, and eye shadow via physics-based manipulation of intrinsics image layers, which preserving the appearance characteristics and lighting conditions of the target face. Continuous Symmetric Stereo with Adaptive Outlier Handling Chen Li, Lap-Fai Yu, Zhichao Lu, Yasuyuki Matsushita, Kun Zhou, Stephen Lin International Conference on 3D Vision (3DV), 2015 [Paper] [Supplementary Material] [Poster] [Bibtex] A stereo matching technique that provides a good combination of accuracy and speed, allowing one to generate high-quality reconstruction of outdoor images even with complex occlusions. Intrinsic Face Image Decomposition with Human Face Priors Chen Li, Kun Zhou, Stephen Lin European Conference on Computer Vision (ECCV), 2014 [Paper] [Supplementary Material] [Poster] [Video] [Bibtex] A special intrinsic image decomposition method for facial images, where human face priors including statistics on skin reflectance and facial geometry are used as constraints to achieve appreciable improvements over more generic techniques. Bayesian Depth-from-Defocus with Shading Constraints Chen Li, Shuochen Su, Yasuyuki Matsushita, Kun Zhou, Stephen Lin IEEE Computer Vision and Pattern Recognition (CVPR), 2013 [Paper] [Poster] [Bibtex] Enhancing the performance of depth-from-defocus through the use of shading information, where depth-from-defocus and shape-from-shading improve each other as well as e ective shape reconstruction of textureless surfaces. Removal of Dust Artifacts in Focal Stack Image Sequences Chen Li, Kun Zhou, Stephen Lin International Conference on Pattern Recognition (ICPR), 2012 [Paper] [Poster] [Bibtex] A technique for removing the appearance of sensor dust in a focal stack image sequence captured with multiple focus settings.
Last update: Sept. 25, 2017