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 Siyu Zhu

Siyu Zhu

FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting


May 15, 2021
Zhiwen Fan, Lingjie Zhu, Honghua Li, Xiaohao Chen, Siyu Zhu, Ping Tan

Figure 1 for FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
Figure 2 for FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
Figure 3 for FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
Figure 4 for FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
* 17 pages, 16 figures 
  Access Paper or Ask Questions

CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution


May 11, 2021
Lizhe Liu, Xiaohao Chen, Siyu Zhu, Ping Tan

Figure 1 for CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
Figure 2 for CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
Figure 3 for CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
Figure 4 for CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution

  Access Paper or Ask Questions

Cluster Contrast for Unsupervised Person Re-Identification


Apr 12, 2021
Zuozhuo Dai, Guangyuan Wang, Weihao Yuan, Siyu Zhu, Ping Tan

Figure 1 for Cluster Contrast for Unsupervised Person Re-Identification
Figure 2 for Cluster Contrast for Unsupervised Person Re-Identification
Figure 3 for Cluster Contrast for Unsupervised Person Re-Identification
Figure 4 for Cluster Contrast for Unsupervised Person Re-Identification

  Access Paper or Ask Questions

Stereo Matching by Self-supervision of Multiscopic Vision


Apr 09, 2021
Weihao Yuan, Yazhan Zhang, Bingkun Wu, Siyu Zhu, Ping Tan, Michael Yu Wang, Qifeng Chen

Figure 1 for Stereo Matching by Self-supervision of Multiscopic Vision
Figure 2 for Stereo Matching by Self-supervision of Multiscopic Vision
Figure 3 for Stereo Matching by Self-supervision of Multiscopic Vision
Figure 4 for Stereo Matching by Self-supervision of Multiscopic Vision

  Access Paper or Ask Questions

Learning Camera Localization via Dense Scene Matching


Mar 31, 2021
Shitao Tang, Chengzhou Tang, Rui Huang, Siyu Zhu, Ping Tan

Figure 1 for Learning Camera Localization via Dense Scene Matching
Figure 2 for Learning Camera Localization via Dense Scene Matching
Figure 3 for Learning Camera Localization via Dense Scene Matching
Figure 4 for Learning Camera Localization via Dense Scene Matching
* CVPR2021 
  Access Paper or Ask Questions

AR Mapping: Accurate and Efficient Mapping for Augmented Reality


Mar 27, 2021
Rui Huang, Chuan Fang, Kejie Qiu, Le Cui, Zilong Dong, Siyu Zhu, Ping Tan

Figure 1 for AR Mapping: Accurate and Efficient Mapping for Augmented Reality
Figure 2 for AR Mapping: Accurate and Efficient Mapping for Augmented Reality
Figure 3 for AR Mapping: Accurate and Efficient Mapping for Augmented Reality
Figure 4 for AR Mapping: Accurate and Efficient Mapping for Augmented Reality
* 8 pages, 14 figures 
  Access Paper or Ask Questions

Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment


Mar 27, 2021
Kejie Qiu, Shenzhou Chen, Jiahui Zhang, Rui Huang, Le Cui, Siyu Zhu, Ping Tan

Figure 1 for Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment
Figure 2 for Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment
Figure 3 for Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment
Figure 4 for Compact 3D Map-Based Monocular Localization Using Semantic Edge Alignment

  Access Paper or Ask Questions

DRO: Deep Recurrent Optimizer for Structure-from-Motion


Mar 25, 2021
Xiaodong Gu, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Chengzhou Tang, Ping Tan

Figure 1 for DRO: Deep Recurrent Optimizer for Structure-from-Motion
Figure 2 for DRO: Deep Recurrent Optimizer for Structure-from-Motion
Figure 3 for DRO: Deep Recurrent Optimizer for Structure-from-Motion
Figure 4 for DRO: Deep Recurrent Optimizer for Structure-from-Motion

  Access Paper or Ask Questions

Single-Shot is Enough: Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs


Mar 24, 2021
Chuan Fang, Shuai Ding, Zilong Dong, Honghua Li, Siyu Zhu, Ping Tan

Figure 1 for Single-Shot is Enough: Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs
Figure 2 for Single-Shot is Enough: Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs
Figure 3 for Single-Shot is Enough: Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs
Figure 4 for Single-Shot is Enough: Panoramic Infrastructure Based Calibration of Multiple Cameras and 3D LiDARs

  Access Paper or Ask Questions

UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation


Feb 06, 2021
Hualie Jiang, Zhe Sheng, Siyu Zhu, Zilong Dong, Rui Huang

Figure 1 for UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
Figure 2 for UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
Figure 3 for UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
Figure 4 for UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
* 9 pages; 5 figures; accepted by IEEE Robotics and Automation Letters; Demo: https://youtu.be/9vm9OMksvrc 
  Access Paper or Ask Questions

MeshMVS: Multi-View Stereo Guided Mesh Reconstruction


Oct 17, 2020
Rakesh Shrestha, Zhiwen Fan, Siyu Zhu, Zuozhuo Dai, Qingkun Su, Ping Tan

Figure 1 for MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
Figure 2 for MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
Figure 3 for MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
Figure 4 for MeshMVS: Multi-View Stereo Guided Mesh Reconstruction

  Access Paper or Ask Questions

Self-Supervised Human Depth Estimation from Monocular Videos


May 07, 2020
Feitong Tan, Hao Zhu, Zhaopeng Cui, Siyu Zhu, Marc Pollefeys, Ping Tan

Figure 1 for Self-Supervised Human Depth Estimation from Monocular Videos
Figure 2 for Self-Supervised Human Depth Estimation from Monocular Videos
Figure 3 for Self-Supervised Human Depth Estimation from Monocular Videos
Figure 4 for Self-Supervised Human Depth Estimation from Monocular Videos
* Accepted by IEEE Conference on Computer Vision and Patten Recognition (CVPR), 2020 
  Access Paper or Ask Questions

End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds


Mar 16, 2020
Lei Li, Siyu Zhu, Hongbo Fu, Ping Tan, Chiew-Lan Tai

Figure 1 for End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
Figure 2 for End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
Figure 3 for End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
Figure 4 for End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
* CVPR 2020. Webpage: https://github.com/craigleili/3DLocalMultiViewDesc 
  Access Paper or Ask Questions

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching


Dec 18, 2019
Xiaodong Gu, Zhiwen Fan, Siyu Zhu, Zuozhuo Dai, Feitong Tan, Ping Tan

Figure 1 for Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Figure 2 for Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Figure 3 for Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Figure 4 for Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

  Access Paper or Ask Questions

A Neural Network for Detailed Human Depth Estimation from a Single Image


Oct 03, 2019
Sicong Tang, Feitong Tan, Kelvin Cheng, Zhaoyang Li, Siyu Zhu, Ping Tan

Figure 1 for A Neural Network for Detailed Human Depth Estimation from a Single Image
Figure 2 for A Neural Network for Detailed Human Depth Estimation from a Single Image
Figure 3 for A Neural Network for Detailed Human Depth Estimation from a Single Image
Figure 4 for A Neural Network for Detailed Human Depth Estimation from a Single Image

  Access Paper or Ask Questions

Matchable Image Retrieval by Learning from Surface Reconstruction


Dec 10, 2018
Tianwei Shen, Zixin Luo, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan

Figure 1 for Matchable Image Retrieval by Learning from Surface Reconstruction
Figure 2 for Matchable Image Retrieval by Learning from Surface Reconstruction
Figure 3 for Matchable Image Retrieval by Learning from Surface Reconstruction
Figure 4 for Matchable Image Retrieval by Learning from Surface Reconstruction
* accepted by ACCV 2018 
  Access Paper or Ask Questions

Batch Feature Erasing for Person Re-identification and Beyond


Nov 17, 2018
Zuozhuo Dai, Mingqiang Chen, Siyu Zhu, Ping Tan

Figure 1 for Batch Feature Erasing for Person Re-identification and Beyond
Figure 2 for Batch Feature Erasing for Person Re-identification and Beyond
Figure 3 for Batch Feature Erasing for Person Re-identification and Beyond
Figure 4 for Batch Feature Erasing for Person Re-identification and Beyond

  Access Paper or Ask Questions

GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints


Aug 16, 2018
Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan

Figure 1 for GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
Figure 2 for GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
Figure 3 for GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
Figure 4 for GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
* Accepted to ECCV'18 
  Access Paper or Ask Questions

Learning and Matching Multi-View Descriptors for Registration of Point Clouds


Jul 16, 2018
Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan

Figure 1 for Learning and Matching Multi-View Descriptors for Registration of Point Clouds
Figure 2 for Learning and Matching Multi-View Descriptors for Registration of Point Clouds
Figure 3 for Learning and Matching Multi-View Descriptors for Registration of Point Clouds
Figure 4 for Learning and Matching Multi-View Descriptors for Registration of Point Clouds

  Access Paper or Ask Questions

Parallel Structure from Motion from Local Increment to Global Averaging


Jun 05, 2017
Siyu Zhu, Tianwei Shen, Lei Zhou, Runze Zhang, Jinglu Wang, Tian Fang, Long Quan

Figure 1 for Parallel Structure from Motion from Local Increment to Global Averaging
Figure 2 for Parallel Structure from Motion from Local Increment to Global Averaging
Figure 3 for Parallel Structure from Motion from Local Increment to Global Averaging
Figure 4 for Parallel Structure from Motion from Local Increment to Global Averaging
* Under review at the International Conference on Computer Vision (ICCV) 2017 
  Access Paper or Ask Questions

Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms


Nov 11, 2014
Christoph Riedl, Richard Zanibbi, Marti A. Hearst, Siyu Zhu, Michael Menietti, Jason Crusan, Ivan Metelsky, Karim R. Lakhani

Figure 1 for Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms
Figure 2 for Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms
Figure 3 for Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms
Figure 4 for Detecting Figures and Part Labels in Patents: Competition-Based Development of Image Processing Algorithms

  Access Paper or Ask Questions