Linchao Bao 
Chinese Characters 

Ph.D.

Principal Researcher at Tencent AI Lab    


Email: linchaobao at gmail dot com 





About Me

I am currently a Principal Researcher at Tencent AI Lab in Shenzhen, China. My research interests are in Computer Vision and Deep Learning. I received my Ph.D. degree in Computer Science from City University of Hong Kong in early 2015. My 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 Computer Vision 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 did another internship in Adobe Camera Raw team for several months, working with Joshua Bury and Eric Chan on Adobe Photoshop and Lightroom algorithms. 

I am looking for research interns to work on computer vision and deep learning at Tencent AI Lab in Shenzhen in 2019. Please drop me an email if you are interested. The intern positions are available anytime during the year, but require full-time working for at least 6 months.



Publications [Google Scholar Citations]
  • 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, and 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, and 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, and Wei Liu. 
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight)
    [PDF]
  • VITAL: VIsual Tracking via Adversarial Learning. 
    Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson Lau, and Ming-Hsuan Yang. 
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight)
    [PDF]
  • Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks. 
    Jiawei Zhang, Jinshan Pan, Jimmy Ren, Yibing Song, Linchao Bao, Rynson Lau, and Ming-Hsuan Yang. 
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (spotlight)
    [PDF]
  • Class-Agnostic Video Object Segmentation without Semantic Re-Identification. 
    Shuangjie Xu, Linchao Bao, and 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, and Ming-Hsuan Yang. 
    Computer Vision and Image Understanding (CVIU), 2017. 
    [PDFproject page]
  • Learning to Hallucinate Face Images via Component Generation and Enhancement. 
    Yibing Song, Jiawei Zhang, Shengfeng He, Linchao Bao, and Qingxiong Yang. 
    International Joint Conference on Artificial Intelligence (IJCAI), 2017. 
    [PDFproject page]
  • Fast Preprocessing for Robust Face Sketch Synthesis. 
    Yibing Song, Jiawei Zhang, Linchao Bao, and Qingxiong Yang. 
    International Joint Conference on Artificial Intelligence (IJCAI), 2017. 
    [PDFproject page]
  • Robust Piecewise-Constant Smoothing: M-Smoother Revisited.
    Linchao Bao and Qingxiong Yang.
    Technical Report, arXiv:1410.7580 [cs.CV], 2014.
    [PDF | Matlab code | BibTex]
  • Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow.
    Linchao Bao, Qingxiong Yang, and Hailin Jin.
    IEEE Transactions on Image Processing (TIP), 2014. (The extension for our CVPR 2014 paper)
    [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, and 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, and 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, and Qingxiong Yang.
    GPU Technology Conference (GTC) Posters, 2014. 
    [PDF poster (200KB) | PDF implementation notes (350KB) | Matlab mex code (win64 | linux) | BibTeX]
  • Real-Time Video Decolorization Using Bilateral Filtering.
    Yibing Song, Linchao Bao, and 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, and 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, and 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, and 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.