pottrait

Xiaowei Zhou

周晓巍

Zhejiang University

About Me

I am a Research Professor in the College of Computer Science & the State Key Laboratory of CAD&CG at Zhejiang University. Before joining ZJU in 2017, I was a postdoctoral researcher at the GRASP Laboratory at University of Pennsylvania. My research interest lies in the field of 3D Computer Vision, particularly including 3D reconstruction, pose estimation, motion capture, and scene understanding, as well as their applications in mixed reality and robotics. I am looking for students, postdocs and research assistants, please drop me an email if you are interested in working with me.

Recent News

  • Seven papers accepted by CVPR and three (conditionally) by SIGGRAPH 2022! (Read More)
  • Invited talk at the 3DGV seminar. (Read More)
  • EasyMocap v0.1 released, checked it out! (Read More)
  • NeuralBody and NeuralRecon selected as CVPR'21 Best Paper Candidates.
  • Join the editorial board of International Journal of Computer Vision.

Selected Publications
Full publication list at Google Scholar

* denotes equal contribution.
Efficient Neural Radiance Fields for Interactive Free-viewpoint Video thumbnail loading...
Efficient Neural Radiance Fields for Interactive Free-viewpoint Video
Haotong LinSida PengZhen XuYunzhi YanQing ShuaiHujun BaoXiaowei Zhou
SIGGRAPH Asia2022 
Reconstructing Hand-Held Objects from Monocular Video thumbnail loading...
Reconstructing Hand-Held Objects from Monocular Video
Di HuangXiaopeng JiXingyi HeJiaming SunTong HeQing ShuaiWanli OuyangXiaowei Zhou
SIGGRAPH Asia2022 
Neural 3D Reconstruction in the Wild
Jiaming SunXi ChenQianqian WangZhengqi LiHadar Averbuch-ElorXiaowei ZhouNoah Snavely
SIGGRAPH2022 
Novel View Synthesis of Human Interactions from Sparse Multi-view Videos
Qing ShuaiChen GengQi FangSida PengWenhao ShenXiaowei ZhouHujun Bao
SIGGRAPH2022 
OnePose: One-Shot Object Pose Estimation without CAD Models
Jiaming* SunZihao* WangSiyu* ZhangXingyi HeHongcheng ZhaoGuofeng ZhangXiaowei Zhou
CVPR2022 
Neural 3D Scene Reconstruction with the Manhattan-world Assumption thumbnail loading...
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
Haoyu GuoSida PengHaotong LinQianqian WangGuofeng ZhangHujun BaoXiaowei Zhou
CVPR2022  Oral Presentation
PlanarRecon: Real-Time 3D Plane Detection and Reconstruction from Posed Monocular Videos
Yiming XieMatheus GadelhaFengting YangXiaowei ZhouHuaizu Jiang
CVPR2022 
Modeling Indirect Illumination for Inverse Rendering thumbnail loading...
Modeling Indirect Illumination for Inverse Rendering
Yuanqing ZhangJiaming SunXingyi HeHuan FuRongfei JiaXiaowei Zhou
CVPR2022 
Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies
Sida Peng*Junting Dong*Qianqian WangShangzhan ZhangQing ShuaiHujun BaoXiaowei Zhou
ICCV2021 
Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
Sida PengYuanqing ZhangYinghao XuQianqian WangQing ShuaiHujun BaoXiaowei Zhou
CVPR2021  Best Paper Candidate
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
Jiaming Sun*Yiming Xie*Linghao ChenXiaowei ZhouHujun Bao
CVPR2021  Best Paper Candidate
Reconstructing 3D Human Pose by Watching Humans in the Mirror
Qi Fang*Qing Shuai*Junting DongHujun BaoXiaowei Zhou
CVPR2021  Oral Presentation
LoFTR: Detector-Free Local Feature Matching with Transformers
Jiaming Sun*Zehong Shen*Yuang Wang*Hujun BaoXiaowei Zhou
CVPR2021 
Pixel-wise Voting Network for 6DoF Object Pose Estimation
Sida Peng*Xiaowei Zhou*Yuan LiuHaotong LinQixing HuangHujun Bao
T-PAMI2020  CVPR 2019 Oral Presentation
Fast and Robust Multi-Person 3D Pose Estimation and Tracking from Multiple Views thumbnail loading...
Fast and Robust Multi-Person 3D Pose Estimation and Tracking from Multiple Views
Junting DongQi FangWen JiangYurou YangQixing HuangHujun BaoXiaowei Zhou
T-PAMI2021 
iMoCap: Motion Capture from Internet Videos
Junting Dong*Qing Shuai*Jingxiang SunYuanqing ZhangHujun BaoXiaowei Zhou
IJCV2022  ECCV 2020 Oral Presentation
Deep Snake thumbnail loading...
Deep Snake for Real-Time Instance Segmentation
Sida PengWen JiangHuaijin PiXiuli LiHujun BaoXiaowei Zhou
CVPR2020  Oral Presentation
Monocap thumbnail loading...
Monocap: Monocular human motion capture using a cnn coupled with a geometric prior
Xiaowei ZhouMenglong ZhuGeorgios PavlakosSpyridon LeonardosKonstantinos G DerpanisKostas Daniilidis
T-PAMI2018 
Coarse-to-fine volumetric prediction for single-image 3D human pose thumbnail loading...
Coarse-to-fine volumetric prediction for single-image 3D human pose
Georgios PavlakosXiaowei ZhouKonstantinos G DerpanisKostas Daniilidis
CVPR2017 

Group

Teaching