Linchao Bao

Ph.D.

Principal Research Scientist & Team Leader
Tencent AI Lab


Email: linchaobao at gmail dot com


About Me

I am currently a Principal Research Scientist and Team Leader at Tencent AI Lab in Shenzhen, China. My research interests are in Computer Vision and Deep Learning. I received my M.S. degree in Pattern Recognition and Intelligent Systems from Huazhong University of Science & Technology and Ph.D. degree in Computer Science from City University of Hong Kong. My Ph.D. supervisor was Dr. Qingxiong Yang. Prior to joining Tencent, I spent a few months working on mapping and localization algorithms for autonomous driving at DiDi Research. Before that, I was an Algorithm Engineer in DJI working on imaging algorithms for drones. During my Ph.D. period, I was a Research Intern at Adobe Research (San Jose, CA, USA) from Nov 2013 to May 2014, working with Dr. Hailin Jin and Dr. Byungmoon Kim. I also worked in Adobe Camera Raw team for several months, working with Joshua Bury and Eric Chan on Adobe Photoshop and Lightroom algorithms.

+. We are looking for research interns (PhD/master students) to work at Tencent AI Lab in Shenzhen in 2021. The position requires full-time working for at least 6 months.

+. A few full-time researcher positions are available for fresh graduates (PhD/master) with top publications. Please drop me an email if you are interested.


Publications [Google Scholar Citations]

  • High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies.
    Linchao Bao*, Xiangkai Lin*, Yajing Chen*, Haoxian Zhang*, Sheng Wang, Xuefei Zhe, Di Kang, Haozhi Huang, Xinwei Jiang, Jue Wang, Dong Yu, Zhengyou Zhang. (*equal contribution)
    ACM Transactions on Graphics (TOG), 2021.
    [PDF | project page | code]
  • Self-Supervised Video Representation Learning by Uncovering Spatio-temporal Statistics.
    Jiangliu Wang, Jianbo Jiao, Linchao Bao*, Shengfeng He, Wei Liu, Yunhui Liu*. (*corresponding author)
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
    [PDF | code]
  • Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders.
    Jing Li, Di Kang, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He, Linchao Bao.
    IEEE International Conference on Computer Vision (ICCV), 2021.
    [PDF | code]
  • Model-based 3D Hand Reconstruction via Self-Supervised Learning.
    Yujin Chen, Zhigang Tu, Di Kang, Linchao Bao, Ying Zhang, Xuefei Zhe, Ruizhi Chen, Junsong Yuan.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [PDF | code]
  • Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation.
    Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Wei Wang, Marco De Nadai.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
    [PDF | code]
  • UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing.
    Meng Cao, Haozhi Huang, Hao Wang, Xuan Wang, Li Shen, Sheng Wang, Linchao Bao*, Zhifeng Li, Jiebo Luo. (*corresponding author)
    IEEE Transactions on Image Processing (TIP), 2021.
    [PDF]
  • Multi-Stage Degradation Homogenization for Super-Resolution of Face Images With Extreme Degradations.
    Liang Chen, Jinshan Pan, Junjun Jiang, Jiawei Zhang, Zhen Han, Linchao Bao*. (*corresponding author)
    IEEE Transactions on Image Processing (TIP), 2021.
    [PDF]
  • Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion.
    Yujin Chen, Zhigang Tu, Di Kang, Ruizhi Chen, Linchao Bao*, Zhengyou Zhang, Junsong Yuan. (*corresponding author)
    IEEE Transactions on Image Processing (TIP), 2021.
    [PDF]
  • Self-supervised Learning of Detailed 3D Face Reconstruction.
    Yajing Chen, Fanzi Wu, Zeyu Wang, Yibing Song, Yonggen Ling, Linchao Bao*. (*corresponding author)
    IEEE Transactions on Image Processing (TIP), 2020.
    [PDF | code]
  • MVF-Net: Multi-View 3D Face Morphable Model Regression.
    Fanzi Wu*, Linchao Bao*, Yajing Chen, Yonggen Ling, Yibing Song, Songnan Li, King N. Ngan, Wei Liu. (*equal contribution)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [PDF | code]
  • MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation.
    Shuangjie Xu, Daizong Liu, Linchao Bao*, Wei Liu, Pan Zhou*. (*corresponding author)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. (oral)
    [PDF | code]
  • Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics.
    Jiangliu Wang, Jianbo Jiao, Linchao Bao*, Shengfeng He, Yunhui Liu, Wei Liu*. (*corresponding author)
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [PDF | code]
  • Face Anti-Spoofing: Model Matters, So Does Data.
    Xiao Yang, Wenhan Luo, Linchao Bao, Yuan Gao, Dihong Gong, Shibao Zheng, Zhifeng Li, Wei Liu.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
    [PDF]
  • Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement.
    Yibing Song, Jiawei Zhang, Lijun Gong, Shengfeng He, Linchao Bao, Jinshan Pan, Qingxiong Yang, Ming-Hsuan Yang.
    International Journal of Computer Vision (IJCV), 2018.
    [PDF]
  • Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial Odometry.
    Yonggen Ling, Linchao Bao, Zequn Jie, Fengming Zhu, Ziyang Li, Shanmin Tang, Yongsheng Liu, Wei Liu, Tong Zhang.
    European Conference on Computer Vision (ECCV), 2018.
    [PDF]
  • CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF.
    Linchao Bao, Baoyuan Wu, Wei Liu.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight oral)
    [PDF]
  • VITAL: VIsual Tracking via Adversarial Learning.
    Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson Lau, Ming-Hsuan Yang.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight oral)
    [PDF]
  • Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks.
    Jiawei Zhang, Jinshan Pan, Jimmy Ren, Yibing Song, Linchao Bao, Rynson Lau, Ming-Hsuan Yang.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight oral)
    [PDF]
  • Class-Agnostic Video Object Segmentation without Semantic Re-Identification.
    Shuangjie Xu, Linchao Bao, Pan Zhou.
    The 2018 DAVIS Challenge on Video Object Segmentation - CVPR Workshops (CVPRW), 2018.
    (We achieved the 3rd place out of 18 teams in the challenge!)
    [PDF]
  • Stylizing Face Images via Multiple Exemplars.
    Yibing Song, Linchao Bao, Shengfeng He, Qingxiong Yang, Ming-Hsuan Yang.
    Computer Vision and Image Understanding (CVIU), 2017.
    [PDF]
  • Learning to Hallucinate Face Images via Component Generation and Enhancement.
    Yibing Song, Jiawei Zhang, Shengfeng He, Linchao Bao, Qingxiong Yang.
    International Joint Conference on Artificial Intelligence (IJCAI), 2017.
    [PDF | project page]
  • Fast Preprocessing for Robust Face Sketch Synthesis.
    Yibing Song, Jiawei Zhang, Linchao Bao, Qingxiong Yang.
    International Joint Conference on Artificial Intelligence (IJCAI), 2017.
    [PDF | project page]
  • Robust Piecewise-Constant Smoothing: M-Smoother Revisited.
    Linchao Bao and Qingxiong Yang.
    arXiv:1410.7580 [cs.CV], 2014.
    [PDF (7.5MB) | low-res. PDF (1.3MB) | project page | Matlab code | BibTex]
  • Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow.
    Linchao Bao, Qingxiong Yang, Hailin Jin.
    IEEE Transactions on Image Processing (TIP), 2014.
    [PDF (24MB) | low-res. PDF (740KB) | project page | Matlab mexw64 code (2.5MB) | github code | BibTex]
  • Real-Time Exemplar-Based Face Sketch Synthesis.
    Yibing Song, Linchao Bao, Qingxiong Yang, Ming-Hsuan Yang.
    European Conference on Computer Vision (ECCV), 2014.
    [PDF (2.7MB) | project page | BibTeX]
  • Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow.
    Linchao Bao, Qingxiong Yang, Hailin Jin.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
    [PDF (5.4MB) | project page | Matlab mexw64 code (2.5MB) | github code | BibTeX]
  • A Comparison of TV-L1 Optical Flow Solvers on GPU.
    Linchao Bao, Hailin Jin, Byungmoon Kim, Qingxiong Yang.
    GPU Technology Conference (GTC), 2014. (poster)
    [PDF poster (200KB) | PDF implementation notes (350KB) | Matlab mex code (win64 | linux) | BibTeX]
  • Real-Time Video Decolorization Using Bilateral Filtering.
    Yibing Song, Linchao Bao, Qingxiong Yang.
    IEEE Winter Conference on Applications of Computer Vision (WACV), 2014.
    [PDF (9.7MB) | low-res. PDF (1.2MB) | pptx slides (10.5MB) | BibTeX]
  • Tree Filtering: Efficient Structure-Preserving Smoothing With a Minimum Spanning Tree.
    Linchao Bao, Yibing Song, Qingxiong Yang, Hao Yuan, Gang Wang.
    IEEE Transactions on Image Processing (TIP), 2014.
    [PDF (3.5MB) | low-res. PDF (950KB) | Matlab demo (mexw64/mexa64) (3MB) | BibTeX]
  • Decolorization: Is rgb2gray() Out?
    Yibing Song, Linchao Bao, Xiaobin Xu, Qingxiong Yang.
    ACM SIGGRAPH Asia Technical Briefs, 2013.
    [PDF (6.8MB) | low-res. PDF (610KB) | project page | BibTex]
  • An Edge-Preserving Filtering Framework for Visibility Restoration.
    Linchao Bao, Yibing Song, Qingxiong Yang, Narendra Ahuja.
    International Conference on Pattern Recognition (ICPR), 2012. (oral)
    [PDF (1.7MB) | pptx slides (5MB) | C++ code (haze removal) (2.3MB) | BibTeX]

Shipped Products

  • DJI Spark Drone: IMU-based Electronic Image Stabilization (EIS).
    I led a team that developed the IMU-based EIS system for DJI Spark drone during 2015~2016.
  • DJI OSMO: Panorama Stitching on Mobile Phones.
    I led a team that developed the panorama photography mode for DJI OSMO in 2015.
  • DJI Phantom 3 & Inspire 1: HDR Photography.
    I developed the HDR mode for the cameras on DJI Phantom 3 and Inspire 1 drones in 2015.
  • Adobe Lightroom 6.0 & Photoshop Camera Raw 9.0: HDR & Panorama Merge.
    Together with Joshua Bury, we developed the algorithms for HDR & Panorama Merge in Adobe Lightroom 6.0 and Photoshop Camera Raw 9.0 in 2014.
  • Adobe Premiere Pro CC: GPU optimized Optical Flow Time Remapping.
    I developed the algorithm for GPU optimized Optical Flow Time Remapping in Adobe Premiere Pro CC in 2014.