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 Xiaowei Zhou

Xiaowei Zhou

NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video


Apr 01, 2021
Jiaming Sun, Yiming Xie, Linghao Chen, Xiaowei Zhou, Hujun Bao

Figure 1 for NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
Figure 2 for NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
Figure 3 for NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
Figure 4 for NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
* Accepted to CVPR 2021 as Oral Presentation. Project page: https://zju3dv.github.io/neuralrecon/ 
  Access Paper or Ask Questions

LoFTR: Detector-Free Local Feature Matching with Transformers


Apr 01, 2021
Jiaming Sun, Zehong Shen, Yuang Wang, Hujun Bao, Xiaowei Zhou

Figure 1 for LoFTR: Detector-Free Local Feature Matching with Transformers
Figure 2 for LoFTR: Detector-Free Local Feature Matching with Transformers
Figure 3 for LoFTR: Detector-Free Local Feature Matching with Transformers
Figure 4 for LoFTR: Detector-Free Local Feature Matching with Transformers
* Accepted to CVPR 2021. Project page: https://zju3dv.github.io/loftr/ 
  Access Paper or Ask Questions

Reconstructing 3D Human Pose by Watching Humans in the Mirror


Apr 01, 2021
Qi Fang, Qing Shuai, Junting Dong, Hujun Bao, Xiaowei Zhou

Figure 1 for Reconstructing 3D Human Pose by Watching Humans in the Mirror
Figure 2 for Reconstructing 3D Human Pose by Watching Humans in the Mirror
Figure 3 for Reconstructing 3D Human Pose by Watching Humans in the Mirror
Figure 4 for Reconstructing 3D Human Pose by Watching Humans in the Mirror
* CVPR 2021 (Oral), project page: https://zju3dv.github.io/Mirrored-Human/ 
  Access Paper or Ask Questions

Generative Transition Mechanism to Image-to-Image Translation via Encoded Transformation


Mar 09, 2021
Yaxin Shi, Xiaowei Zhou, Ping Liu, Ivor Tsang

* 10 pages, 9 figures 
  Access Paper or Ask Questions

Human-Understandable Decision Making for Visual Recognition


Mar 05, 2021
Xiaowei Zhou, Jie Yin, Ivor Tsang, Chen Wang

Figure 1 for Human-Understandable Decision Making for Visual Recognition
Figure 2 for Human-Understandable Decision Making for Visual Recognition
Figure 3 for Human-Understandable Decision Making for Visual Recognition
Figure 4 for Human-Understandable Decision Making for Visual Recognition
* 12 pages 
  Access Paper or Ask Questions

Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans


Dec 31, 2020
Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou

Figure 1 for Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
Figure 2 for Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
Figure 3 for Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
Figure 4 for Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
* Project page: https://zju3dv.github.io/neuralbody/ 
  Access Paper or Ask Questions

Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction


Dec 14, 2020
Jiafa He, Chengwei Pan, Can Yang, Ming Zhang, Yang Wang, Xiaowei Zhou, Yizhou Yu

Figure 1 for Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
Figure 2 for Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
Figure 3 for Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
Figure 4 for Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction
* MICCAI 2020 
  Access Paper or Ask Questions

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation


Aug 26, 2020
Jianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu, Wei Jiang, Hujun Bao, Xiaowei Zhou

Figure 1 for SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Figure 2 for SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Figure 3 for SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Figure 4 for SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
* ECCV 2020, project page: https://zju3dv.github.io/SMAP/ 
  Access Paper or Ask Questions

Motion Capture from Internet Videos


Aug 19, 2020
Junting Dong, Qing Shuai, Yuanqing Zhang, Xian Liu, Xiaowei Zhou, Hujun Bao

Figure 1 for Motion Capture from Internet Videos
Figure 2 for Motion Capture from Internet Videos
Figure 3 for Motion Capture from Internet Videos
Figure 4 for Motion Capture from Internet Videos
* ECCV 2020 (Oral), project page: https://zju3dv.github.io/iMoCap/ 
  Access Paper or Ask Questions

Coherent Reconstruction of Multiple Humans from a Single Image


Jun 15, 2020
Wen Jiang, Nikos Kolotouros, Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis

Figure 1 for Coherent Reconstruction of Multiple Humans from a Single Image
Figure 2 for Coherent Reconstruction of Multiple Humans from a Single Image
Figure 3 for Coherent Reconstruction of Multiple Humans from a Single Image
Figure 4 for Coherent Reconstruction of Multiple Humans from a Single Image
* CVPR 2020. Project Page: https://jiangwenpl.github.io/multiperson/ 
  Access Paper or Ask Questions

Learning Feature Descriptors using Camera Pose Supervision


Apr 28, 2020
Qianqian Wang, Xiaowei Zhou, Bharath Hariharan, Noah Snavely

Figure 1 for Learning Feature Descriptors using Camera Pose Supervision
Figure 2 for Learning Feature Descriptors using Camera Pose Supervision
Figure 3 for Learning Feature Descriptors using Camera Pose Supervision
Figure 4 for Learning Feature Descriptors using Camera Pose Supervision

  Access Paper or Ask Questions

Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation


Apr 07, 2020
Jiaming Sun, Linghao Chen, Yiming Xie, Siyu Zhang, Qinhong Jiang, Xiaowei Zhou, Hujun Bao

Figure 1 for Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Figure 2 for Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Figure 3 for Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
Figure 4 for Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
* Accepted to CVPR 2020. Code is available at https://github.com/zju3dv/disprcnn 
  Access Paper or Ask Questions

EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery


Mar 24, 2020
Min Wang, Feng Qiu, Wentao Liu, Chen Qian, Xiaowei Zhou, Lizhuang Ma

Figure 1 for EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery
Figure 2 for EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery
Figure 3 for EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery
Figure 4 for EllipBody: A Light-weight and Part-based Representation for Human Pose and Shape Recovery

  Access Paper or Ask Questions

Deep Snake for Real-Time Instance Segmentation


Jan 06, 2020
Sida Peng, Wen Jiang, Huaijin Pi, Hujun Bao, Xiaowei Zhou

Figure 1 for Deep Snake for Real-Time Instance Segmentation
Figure 2 for Deep Snake for Real-Time Instance Segmentation
Figure 3 for Deep Snake for Real-Time Instance Segmentation
Figure 4 for Deep Snake for Real-Time Instance Segmentation

  Access Paper or Ask Questions

GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs


Nov 14, 2019
Yuan Liu, Zehong Shen, Zhixuan Lin, Sida Peng, Hujun Bao, Xiaowei Zhou

Figure 1 for GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
Figure 2 for GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
Figure 3 for GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
Figure 4 for GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
* Accepted by NeurIPS 2019 
  Access Paper or Ask Questions

Latent Adversarial Defence with Boundary-guided Generation


Jul 16, 2019
Xiaowei Zhou, Ivor W. Tsang, Jie Yin

Figure 1 for Latent Adversarial Defence with Boundary-guided Generation
Figure 2 for Latent Adversarial Defence with Boundary-guided Generation
Figure 3 for Latent Adversarial Defence with Boundary-guided Generation
Figure 4 for Latent Adversarial Defence with Boundary-guided Generation
* 11 pages 
  Access Paper or Ask Questions

Learning Transformation Synchronization


Jan 27, 2019
Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, Qixing Huang

Figure 1 for Learning Transformation Synchronization
Figure 2 for Learning Transformation Synchronization
Figure 3 for Learning Transformation Synchronization
Figure 4 for Learning Transformation Synchronization

  Access Paper or Ask Questions

Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views


Jan 14, 2019
Junting Dong, Wen Jiang, Qixing Huang, Hujun Bao, Xiaowei Zhou

Figure 1 for Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
Figure 2 for Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
Figure 3 for Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
Figure 4 for Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
* Project page: https://zju-3dv.github.io/mvpose/ 
  Access Paper or Ask Questions

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion


Jan 05, 2019
Zhenpei Yang, Jeffrey Z. Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman, Qixing Huang

Figure 1 for Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Figure 2 for Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Figure 3 for Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Figure 4 for Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
* fixed issues with bibtex file 
  Access Paper or Ask Questions

Path-Invariant Map Networks


Jan 05, 2019
Zaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou, Qixing Huang

Figure 1 for Path-Invariant Map Networks
Figure 2 for Path-Invariant Map Networks
Figure 3 for Path-Invariant Map Networks
Figure 4 for Path-Invariant Map Networks

  Access Paper or Ask Questions

PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation


Dec 31, 2018
Sida Peng, Yuan Liu, Qixing Huang, Hujun Bao, Xiaowei Zhou

Figure 1 for PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
Figure 2 for PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
Figure 3 for PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
Figure 4 for PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation
* The first two authors contributed equally to this paper. Project page: https://zju-3dv.github.io/pvnet/ 
  Access Paper or Ask Questions

Ordinal Depth Supervision for 3D Human Pose Estimation


May 10, 2018
Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis

Figure 1 for Ordinal Depth Supervision for 3D Human Pose Estimation
Figure 2 for Ordinal Depth Supervision for 3D Human Pose Estimation
Figure 3 for Ordinal Depth Supervision for 3D Human Pose Estimation
Figure 4 for Ordinal Depth Supervision for 3D Human Pose Estimation
* CVPR 2018 Camera Ready 
  Access Paper or Ask Questions

Learning to Estimate 3D Human Pose and Shape from a Single Color Image


May 10, 2018
Georgios Pavlakos, Luyang Zhu, Xiaowei Zhou, Kostas Daniilidis

Figure 1 for Learning to Estimate 3D Human Pose and Shape from a Single Color Image
Figure 2 for Learning to Estimate 3D Human Pose and Shape from a Single Color Image
Figure 3 for Learning to Estimate 3D Human Pose and Shape from a Single Color Image
Figure 4 for Learning to Estimate 3D Human Pose and Shape from a Single Color Image
* CVPR 2018 Camera Ready 
  Access Paper or Ask Questions

Multi-Image Semantic Matching by Mining Consistent Features


May 01, 2018
Qianqian Wang, Xiaowei Zhou, Kostas Daniilidis

Figure 1 for Multi-Image Semantic Matching by Mining Consistent Features
Figure 2 for Multi-Image Semantic Matching by Mining Consistent Features
Figure 3 for Multi-Image Semantic Matching by Mining Consistent Features
Figure 4 for Multi-Image Semantic Matching by Mining Consistent Features
* CVPR 2018 
  Access Paper or Ask Questions

Human Motion Capture Using a Drone


Apr 17, 2018
Xiaowei Zhou, Sikang Liu, Georgios Pavlakos, Vijay Kumar, Kostas Daniilidis

Figure 1 for Human Motion Capture Using a Drone
Figure 2 for Human Motion Capture Using a Drone
Figure 3 for Human Motion Capture Using a Drone
Figure 4 for Human Motion Capture Using a Drone
* In International Conference on Robotics and Automation (ICRA) 2018 
  Access Paper or Ask Questions

MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior


Mar 09, 2018
Xiaowei Zhou, Menglong Zhu, Georgios Pavlakos, Spyridon Leonardos, Kostantinos G. Derpanis, Kostas Daniilidis

Figure 1 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 2 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 3 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
Figure 4 for MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior
* Accepted by PAMI. Extended version of the following paper: Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video. X Zhou, M Zhu, S Leonardos, K Derpanis, K Daniilidis. CVPR 2016. arXiv admin note: substantial text overlap with arXiv:1511.09439 
  Access Paper or Ask Questions

Polar Transformer Networks


Feb 01, 2018
Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis

Figure 1 for Polar Transformer Networks
Figure 2 for Polar Transformer Networks
Figure 3 for Polar Transformer Networks
Figure 4 for Polar Transformer Networks
* Accepted as a conference paper at ICLR 2018 
  Access Paper or Ask Questions

Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose


Jul 26, 2017
Georgios Pavlakos, Xiaowei Zhou, Konstantinos G. Derpanis, Kostas Daniilidis

Figure 1 for Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Figure 2 for Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Figure 3 for Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
Figure 4 for Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
* CVPR 2017 Camera Ready. Project Page: https://www.seas.upenn.edu/~pavlakos/projects/volumetric/ 
  Access Paper or Ask Questions

6-DoF Object Pose from Semantic Keypoints


Mar 14, 2017
Georgios Pavlakos, Xiaowei Zhou, Aaron Chan, Konstantinos G. Derpanis, Kostas Daniilidis

Figure 1 for 6-DoF Object Pose from Semantic Keypoints
Figure 2 for 6-DoF Object Pose from Semantic Keypoints
Figure 3 for 6-DoF Object Pose from Semantic Keypoints
Figure 4 for 6-DoF Object Pose from Semantic Keypoints
* IEEE International Conference on Robotics and Automation (ICRA), 2017 
  Access Paper or Ask Questions