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

Hongdong Li

Ranking Models in Unlabeled New Environments


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

Figure 1 for Ranking Models in Unlabeled New Environments
Figure 2 for Ranking Models in Unlabeled New Environments
Figure 3 for Ranking Models in Unlabeled New Environments
Figure 4 for Ranking Models in Unlabeled New Environments
* 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

Figure 1 for Blind Image Decomposition
Figure 2 for Blind Image Decomposition
Figure 3 for Blind Image Decomposition
Figure 4 for Blind Image Decomposition
* 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

Figure 1 for Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
Figure 2 for Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
Figure 3 for Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
Figure 4 for Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
* 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

Figure 1 for Multi-level Motion Attention for Human Motion Prediction
Figure 2 for Multi-level Motion Attention for Human Motion Prediction
Figure 3 for Multi-level Motion Attention for Human Motion Prediction
Figure 4 for Multi-level Motion Attention for Human Motion Prediction
* 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

Figure 1 for Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding
Figure 2 for Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding
Figure 3 for Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding
Figure 4 for Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding

  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

Figure 1 for Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
Figure 2 for Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
Figure 3 for Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
Figure 4 for Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
* 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

Figure 1 for Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior
Figure 2 for Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior
Figure 3 for Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior
Figure 4 for Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior

  Access Paper or Ask Questions

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


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

Figure 1 for Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
Figure 2 for Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
Figure 3 for Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
Figure 4 for Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
* 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

Figure 1 for One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet
Figure 2 for One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet
Figure 3 for One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet
Figure 4 for One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet

  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

Figure 1 for Learning to Estimate Hidden Motions with Global Motion Aggregation
Figure 2 for Learning to Estimate Hidden Motions with Global Motion Aggregation
Figure 3 for Learning to Estimate Hidden Motions with Global Motion Aggregation
Figure 4 for Learning to Estimate Hidden Motions with Global Motion Aggregation

  Access Paper or Ask Questions

Learning Optical Flow from a Few Matches


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

Figure 1 for Learning Optical Flow from a Few Matches
Figure 2 for Learning Optical Flow from a Few Matches
Figure 3 for Learning Optical Flow from a Few Matches
Figure 4 for Learning Optical Flow from a Few Matches
* 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

Figure 1 for Self-Supervised Visibility Learning for Novel View Synthesis
Figure 2 for Self-Supervised Visibility Learning for Novel View Synthesis
Figure 3 for Self-Supervised Visibility Learning for Novel View Synthesis
Figure 4 for Self-Supervised Visibility Learning for Novel View Synthesis
* 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

Figure 1 for Deep Two-View Structure-from-Motion Revisited
Figure 2 for Deep Two-View Structure-from-Motion Revisited
Figure 3 for Deep Two-View Structure-from-Motion Revisited
Figure 4 for Deep Two-View Structure-from-Motion Revisited
* 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

Figure 1 for Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework
Figure 2 for Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework
Figure 3 for Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework
Figure 4 for Enhanced Spatio-Temporal Interaction Learning for Video Deraining: A Faster and Better Framework

  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

Figure 1 for Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors
Figure 2 for Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors
Figure 3 for Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors
Figure 4 for Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors

  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

Figure 1 for Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal
Figure 2 for Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal
Figure 3 for Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal
Figure 4 for Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal

  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

Figure 1 for ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
Figure 2 for ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
Figure 3 for ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
Figure 4 for ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
* 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

Figure 1 for Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
Figure 2 for Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
Figure 3 for Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
Figure 4 for Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
* 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

Figure 1 for Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
Figure 2 for Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
Figure 3 for Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
Figure 4 for Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
* 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

Figure 1 for Depth Completion using Piecewise Planar Model
Figure 2 for Depth Completion using Piecewise Planar Model
Figure 3 for Depth Completion using Piecewise Planar Model
Figure 4 for Depth Completion using Piecewise Planar Model
* 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

Figure 1 for Efficient Depth Completion Using Learned Bases
Figure 2 for Efficient Depth Completion Using Learned Bases
Figure 3 for Efficient Depth Completion Using Learned Bases
Figure 4 for Efficient Depth Completion Using Learned Bases
* 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

Figure 1 for PlueckerNet: Learn to Register 3D Line Reconstructions
Figure 2 for PlueckerNet: Learn to Register 3D Line Reconstructions
Figure 3 for PlueckerNet: Learn to Register 3D Line Reconstructions
Figure 4 for PlueckerNet: Learn to Register 3D Line Reconstructions
* 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

Figure 1 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 2 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 3 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
Figure 4 for Displacement-Invariant Cost Computation for Efficient Stereo Matching
* 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

Figure 1 for Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
Figure 2 for Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
Figure 3 for Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
Figure 4 for Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration

  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

Figure 1 for Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Figure 2 for Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Figure 3 for Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Figure 4 for Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
* 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

Figure 1 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 2 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 3 for Hierarchical Neural Architecture Search for Deep Stereo Matching
Figure 4 for Hierarchical Neural Architecture Search for Deep Stereo Matching
* Accepted at NeurIPS 2020; Xuelian Cheng and Yiran Zhong made equal contribution 
  Access Paper or Ask Questions