Chenyangguang Zhang

Chenyangguang (Cyrus) Zhang (张晨阳光)

Master student at Department of Automation, Tsinghua University

Incoming PhD student at CVG, ETH Zurich

Email: zcyg22@mails.tsinghua.edu.cn

Google Scholar • GitHub• LinkedIn

I am a final year Master student at BBNC Lab, Department of Automation, Tsinghua University, supervised by Prof. Dr. Xiangyang Ji. I got my bachelor's degree also from Department of Automation, Tsinghua University. I'm a incoming PhD student at CVG, ETH Zurich, supervised by Prof. Dr. Marc Pollefeys.

My research interest lies in 3D computer vision, especially scene reconstruction and understanding, human-scene interaction and pose estimation.

Some of my close colllaborators include PD Dr. Federico Tombari, Dr. Francis Engelmann, Dr. Yan Di, Dr. Gu Wang, Fangjinhua Wang and Ruida Zhang.

I am invited as a reviewer for CVPR, ICCV and ECCV. I'm a student member of Chinese Society of Image and Graphics (CSIG).

News

[Mar, 2025] Glad to start an internship at Dexmal doing something interesting about whole body control.
[Mar, 2025] My co-authored work GDRNPP is accepted by TPAMI. It has been SOTA on BOP challenge since 2022.
[Feb, 2025] My first-authored paper OpenFunGraph is accepted by CVPR 2025. It proposes a functional scene graph representation to model indoor functionality and interaction.
[Feb, 2025] Two co-authored papers are accepted by CVPR 2025. UNOPose for unseen object pose estimation with an RGB-D reference. GIVEPose for RGB-based category-level object pose estimation.
[Oct, 2024] Two co-authored papers are presented at ECCV 2024. D-SCo for diffusion-based hand-held object reconstruction. LaPose for RGB-based category-level object pose estimation.
[May, 2024] My co-first-authored paper RaSim is presented in ICRA 2024. It involves a useful pipeline for simulating real-world depth scan and completing defected depth maps.
[Feb, 2024] Three my (co-)first-authored papers are accepted by CVPR 2024, including MOHO for single-view hand-held object reconstruction without 3D supervision; KP-RED for shape analysis without part annotations; ShapeMatcher for indoor shape analysis from arbitrary poses.
[Feb, 2024] I'm approved to enroll as an project mobility student to CVG, ETH Zurich. Great thanks for Prof. Marc Pollefeys for giving this opportunity!
[Oct, 2023] Our work GPose2023 wins BOP Challenge 2023, ICCV R6D Workshop. It's honored for me to give an oral presentation in ICCV 2023.
[Sept, 2023] My first-authored paper DDF-HO on single-view hand-held object reconstruction is accepted by NeurIPS 2023.
[July, 2023] My co-first-authored paper U-RED on unsupervised shape retrieval and deformation in indoor scenes is accepted by ICCV 2023.

Selected Publications and Contests

Theme 1: Reconstructing and Understanding Human-Scene Interaction
	Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces Chenyangguang Zhang, Alexandros Delitzas, Fangjinhua Wang, Ruida Zhang, Xiangyang Ji, Marc Pollefeys, Francis Engelmann Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Paper
	MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision Chenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang, Ziqin Huang, Ruida Zhang, Fabian Manhardt, Bowen Fu, Federico Tombari, Xiangyang Ji Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper \| Code \| Poster
	DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field Chenyangguang Zhang, Yan Di, Ruida Zhang, Guangyao Zhai, Fabian Manhardt, Federico Tombari, Xiangyang Ji Conference on Neural Information Processing Systems (NeurIPS), 2023. Paper* \| Code \| Poster
Theme 2: Object-Centric Indoor Scene Reconstruction
	ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation Yan Di, Chenyangguang Zhang, Chaowei Wang, Ruida Zhang, Guangyao Zhai, Yanyan Li, Bowen Fu, Xiangyang Ji, Shan Gao Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper* \| Code
	KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation Ruida Zhang, Chenyangguang Zhang, Yan Di, Fabian Manhardt, Xingyu Liu, Federico Tombari, Xiangyang Ji Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper \| Code
	U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds Yan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Rambach, Didier Stricker, Xiangyang Ji, Federico Tombari International Conference on Computer Vision (ICCV), 2023. Paper* \| Code
Theme 3: MVS and Pose Estimation
	SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance Chenyangguang Zhang, Zhiqiang Lou, Yan Di, Federico Tombari, Xiangyang Ji IEEE International Conference on Multimedia and Expo (ICME), 2023 (oral). Paper\| Oral Presentation Slides
	GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Gu Wang, Jiwen Tang, Zhigang Li, Xiangyang Ji IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. Winner of BOP Challenge 2022 @ ECCV R6D Workshop. Paper\| Slides \| Code
	GPose2023: A Modularized Learning-based Object Pose Estimator Ruida Zhang, Ziqin Huang, Gu Wang, Xingyu Liu, Chenyangguang Zhang, Xiangyang Ji International Conference on Computer Vision Workshop (ICCVW), 2023. Winner of BOP Challenge 2023 @ ICCV R6D Workshop. Oral Presentation Slides

Work Experiences and Interships

Dexmal: Whole body control for quadrupeds, 2025
CVG, ETH Zurich: Project mobility student for 3D computer vision, supervised by Prof. Marc Pollefeys, and daily advised by Dr. Francis Engelmann and Fangjinhua Wang, 2024
Definite Capital: Machine learning for quantitative trades, where I worked with Dr. Rui Xu and Dr. Yu Xiong, 2023
TikTok: 3D scene reconstruction for VR, where I worked with Dr. Peng Wang, 2022
LinkedSee: Machine learning for AIOPS, where I worked with AP Dr. Tong Jia, 2022
Meituan: Real-time 3D mapping for UAV, where I'm supervised by Prof. Dr. Guoquan Huang, 2021
Tencent Games: Backend developer for game servers, 2021

Honors and Awards

Li Yanda Scholarship, 2024
Tianma Intelligent Control Scholarship, 2023
China Optics Valley Scholarship, 2021
Outstanding Student of THU, 2021
Tang Lixin Excellent Scholarship, 2020.
Good Reading Scholarship, THU, 2019.

Miscellaneous

I love sports. I enjoy playing soccer⚽ and badminton🏸, etc. and serve as a winger of soccer team of DA, THU. I'm a soccer fans of Man. Utd. and José Mourinho.

I'm also interested in writing novels and poems. Some of my works are published on Chinese literary magazines. My Wechat official account is named "了妄", where I share some literary works I wrote.

I'm a guitar player admiring Tommy Emmanuel and Kotaro Oshio. Meanwhile, I'm a figure skating fans of Yuzuru Hanyu.

Feel free to get in touch!

Theme 1: Reconstructing and Understanding Human-Scene Interaction
	Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces Chenyangguang Zhang, Alexandros Delitzas, Fangjinhua Wang, Ruida Zhang, Xiangyang Ji, Marc Pollefeys, Francis Engelmann Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Paper
	MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision Chenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang, Ziqin Huang, Ruida Zhang, Fabian Manhardt, Bowen Fu, Federico Tombari, Xiangyang Ji Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper \| Code \| Poster
	DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field Chenyangguang Zhang, Yan Di, Ruida Zhang, Guangyao Zhai, Fabian Manhardt, Federico Tombari, Xiangyang Ji Conference on Neural Information Processing Systems (NeurIPS), 2023. Paper* \| Code \| Poster
Theme 2: Object-Centric Indoor Scene Reconstruction
	ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation Yan Di, Chenyangguang Zhang, Chaowei Wang, Ruida Zhang, Guangyao Zhai, Yanyan Li, Bowen Fu, Xiangyang Ji, Shan Gao Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper* \| Code
	KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation Ruida Zhang, Chenyangguang Zhang, Yan Di, Fabian Manhardt, Xingyu Liu, Federico Tombari, Xiangyang Ji Conference on Computer Vision and Pattern Recognition (CVPR), 2024. Paper \| Code
	U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds Yan Di, Chenyangguang Zhang, Ruida Zhang, Fabian Manhardt, Yongzhi Su, Jason Rambach, Didier Stricker, Xiangyang Ji, Federico Tombari International Conference on Computer Vision (ICCV), 2023. Paper* \| Code
Theme 3: MVS and Pose Estimation
	SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidance Chenyangguang Zhang, Zhiqiang Lou, Yan Di, Federico Tombari, Xiangyang Ji IEEE International Conference on Multimedia and Expo (ICME), 2023 (oral). Paper\| Oral Presentation Slides
	GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Gu Wang, Jiwen Tang, Zhigang Li, Xiangyang Ji IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. Winner of BOP Challenge 2022 @ ECCV R6D Workshop. Paper\| Slides \| Code
	GPose2023: A Modularized Learning-based Object Pose Estimator Ruida Zhang, Ziqin Huang, Gu Wang, Xingyu Liu, Chenyangguang Zhang, Xiangyang Ji International Conference on Computer Vision Workshop (ICCVW), 2023. Winner of BOP Challenge 2023 @ ICCV R6D Workshop. Oral Presentation Slides