Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Hongdong Li

Ranking Models in Unlabeled New Environments


Sep 06, 2021
Xiaoxiao Sun, Yunzhong Hou, Weijian Deng, Hongdong Li, Liang Zheng

* 13 pages, 10 figures, ICCV2021 

  Access Paper or Ask Questions

Blind Image Decomposition


Aug 28, 2021
Junlin Han, Weihao Li, Pengfei Fang, Chunyi Sun, Jie Hong, Mohammad Ali Armin, Lars Petersson, Hongdong Li

* Project page: https://junlinhan.github.io/projects/BID.html. Code: https://github.com/JunlinHan/BID 

  Access Paper or Ask Questions

Underwater Image Restoration via Contrastive Learning and a Real-world Dataset


Jun 20, 2021
Junlin Han, Mehrdad Shoeiby, Tim Malthus, Elizabeth Botha, Janet Anstee, Saeed Anwar, Ran Wei, Mohammad Ali Armin, Hongdong Li, Lars Petersson

* In submission, code/dataset are at https://github.com/JunlinHan/CWR. arXiv admin note: text overlap with arXiv:2103.09697 

  Access Paper or Ask Questions

Multi-level Motion Attention for Human Motion Prediction


Jun 17, 2021
Wei Mao, Miaomiao Liu, Mathieu Salzmann, Hongdong Li

* Accepted by IJCV. arXiv admin note: substantial text overlap with arXiv:2007.11755 

  Access Paper or Ask Questions

Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding


May 27, 2021
Wenjia Niu, Kaihao Zhang, Wenhan Luo, Yiran Zhong, Xin Yu, Hongdong Li


  Access Paper or Ask Questions

Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance


May 25, 2021
Ziang Cheng, Hongdong Li, Yuta Asano, Yinqiang Zheng, Imari Sato

* Accepted to CVPR2021 

  Access Paper or Ask Questions

Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior


May 09, 2021
Kaihao Zhang, Wenhan Luo, Yanjiang Yu, Wenqi Ren, Fang Zhao, Changsheng Li, Lin Ma, Wei Liu, Hongdong Li


  Access Paper or Ask Questions

Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo


Apr 20, 2021
Junxuan Li, Hongdong Li, Yasuyuki Matsushita

* Accepted to CVPR 2021. Codes in: https://github.com/junxuan-li/LRG_360Panoramic 

  Access Paper or Ask Questions

One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet


Apr 11, 2021
Ziang Cheng, Hongdong Li, Richard Hartley, Yinqiang Zheng, Imari Sato


  Access Paper or Ask Questions

Learning to Estimate Hidden Motions with Global Motion Aggregation


Apr 06, 2021
Shihao Jiang, Dylan Campbell, Yao Lu, Hongdong Li, Richard Hartley


  Access Paper or Ask Questions

Learning Optical Flow from a Few Matches


Apr 05, 2021
Shihao Jiang, Yao Lu, Hongdong Li, Richard Hartley

* Accepted to CVPR 2021 

  Access Paper or Ask Questions

Self-Supervised Visibility Learning for Novel View Synthesis


Apr 04, 2021
Yujiao Shi, Hongdong Li, Xin Yu

* accepted to CVPR2021 

  Access Paper or Ask Questions

Deep Two-View Structure-from-Motion Revisited


Apr 01, 2021
Jianyuan Wang, Yiran Zhong, Yuchao Dai, Stan Birchfield, Kaihao Zhang, Nikolai Smolyanskiy, Hongdong Li

* Accepted at CVPR 2021; Yiran Zhong and Jianyuan Wang contribute equally to this work and the name listed in alphabetical order 

  Access Paper or Ask Questions

Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework


Mar 23, 2021
Kaihao Zhang, Dongxu Li, Wenhan Luo, Wen-Yan Lin, Fang Zhao, Wenqi Ren, Wei Liu, Hongdong Li


  Access Paper or Ask Questions

Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors


Mar 21, 2021
Kaihao Zhang, Rongqing Li, Yanjiang Yu, Wenhan Luo, Changsheng Li, Hongdong Li


  Access Paper or Ask Questions

Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal


Mar 12, 2021
Kaihao Zhang, Dongxu Li, Wenhan Luo, Wenqi Ren, Lin Ma, Hongdong Li


  Access Paper or Ask Questions

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring


Mar 07, 2021
Dongxu Li, Chenchen Xu, Kaihao Zhang, Xin Yu, Yiran Zhong, Wenqi Ren, Hanna Suominen, Hongdong Li

* Preprint for CVPR 2021 Poster 

  Access Paper or Ask Questions

Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery


Mar 05, 2021
Yujiao Shi, Dylan Campbell, Xin Yu, Hongdong Li

* submitted to TPAMI in Aug, 2020 

  Access Paper or Ask Questions

Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment


Dec 16, 2020
Yi Zhou, Hongdong Li, Laurent Kneip

* IEEE Transactions on Robotics ( Volume: 35, Issue: 1, Feb. 2019) 

  Access Paper or Ask Questions

Depth Completion using Piecewise Planar Model


Dec 06, 2020
Yiran Zhong, Yuchao Dai, Hongdong Li

* This work was accomplished in 2017 

  Access Paper or Ask Questions

Efficient Depth Completion Using Learned Bases


Dec 02, 2020
Yiran Zhong, Yuchao Dai, Hongdong Li

* This work was accomplished in 2017 

  Access Paper or Ask Questions

PlueckerNet: Learn to Register 3D Line Reconstructions


Dec 02, 2020
Liu Liu, Hongdong Li, Haodong Yao, Ruyi Zha

* 12 pages 

  Access Paper or Ask Questions

Displacement-Invariant Cost Computation for Efficient Stereo Matching


Dec 01, 2020
Yiran Zhong, Charles Loop, Wonmin Byeon, Stan Birchfield, Yuchao Dai, Kaihao Zhang, Alexey Kamenev, Thomas Breuel, Hongdong Li, Jan Kautz

* 8 pages 

  Access Paper or Ask Questions

Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration


Dec 01, 2020
Liyuan Pan, Shah Chowdhury, Richard Hartley, Miaomiao Liu, Hongguang Zhang, Hongdong Li


  Access Paper or Ask Questions

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation


Oct 28, 2020
Jianyuan Wang, Yiran Zhong, Yuchao Dai, Kaihao Zhang, Pan Ji, Hongdong Li

* NeurIPS 2020, 9 pages 

  Access Paper or Ask Questions

Hierarchical Neural Architecture Search for Deep Stereo Matching


Oct 26, 2020
Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, Zongyuan Ge

* Accepted at NeurIPS 2020; Xuelian Cheng and Yiran Zhong made equal contribution 

  Access Paper or Ask Questions