Ruida Zhang (张睿达)

I am a Ph.D. student at Tsinghua University, supervised by Prof. Xiangyang Ji. Previously, I received my B.E. degree in Automation Engineering at Tsinghua University.

I work on 3D computer vision for robotics, particularly in object pose estimation, 3D reconstruction, and scene understanding, aiming to bridge semantic perception with physical interaction.

I served as a reviewer for CVPR, ICCV, ECCV, NeurIPS, ICLR, AAAI, TPAMI, ACM MM, RAL, TCSVT.

I will graduate in Summer 2027 and am actively seeking job opportunities. Feel free to contact me.

Email  /  Google Scholar  /  Github

profile photo
News
  • [2025.10] Our solution won 2025 Bin-Picking Perception Challenge. It has published in ICCV 2025 R6D Workshop .
  • [2025.07] Our paper ''Street Gaussians without 3D Object Tracker'' is accepted to ICCV2025. It eliminates the reliance on 3D object tracker to enhance generalization ability of street scene reconstruction for autonomous driving.
  • [2025.05] I join MSC lab of UC Berkeley as a visiting student supervised by Masayoshi Tomizuka.
  • [2025.03] My work GDRNPP is accepted by TPAMI. It has been SOTA on BOP challenge since 2022.
  • [2024.09] I join CVRP lab of NUS as a visiting student supervised by Gim Hee Lee.
  • [2024.07] Our paper LaPose on RGB-based category-level object pose estimation is accepted to ECCV2024.
  • [2024.02] 4 papers are accepted to CVPR2024. KP-RED and ShapeMaker focus on joint shape canonicalization, segmentation, retrieval and deformation. SecondPose outperforms competitors on category-level pose estimation. MOHO leverages multi-view information for hand-held object reconstruction.
  • [2023.10] Our work GPose2023 wins BOP Challenge 2023, ICCV R6D Workshop.
  • [2023.09] Our paper DDF-HO on hand-held object reconstruction is accepted to NeurIPS2023.
  • [2023.07] Our paper U-RED on unsupervised shape retrieval and deformation is accepted to ICCV2023.
  • [2022.06] Our category-level pose estimation works GPV-Pose, RBP-Pose, SSP-Pose are accepted to CVPR2022, ECCV2022, IROS2022 respectively.
Selected Publications
Theme 1: Object Pose Estimation
Image 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
Paper / Slides / Code
Image LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
Ruida Zhang, Ziqin Huang, Gu Wang, Chenyangguang Zhang, Yan Di, Xingxing Zuo, Jiwen Tang, Xiangyang Ji
European Conference on Computer Vision (ECCV), 2024
Paper / Code

Image RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation
Ruida Zhang*, Yan Di*, Zhiqiang Lou, Fabian Manhardt, Federico Tombari, Xiangyang Ji
European Conference on Computer Vision (ECCV), 2022
Paper / Code

Image SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation
Ruida Zhang*, Yan Di*, Fabian Manhardt, Federico Tombari, Xiangyang Ji
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Paper

Image GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting
Yan Di*, Ruida Zhang*, Zhiqiang Lou, Fabian Manhardt, Xiangyang Ji, Nassir Navab Federico Tombari
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
Paper / Code

Theme 2: Object-Centric Indoor Scene Reconstruction
Image 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
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Paper / Code

Image 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
37th Conference on Neural Information Processing Systems (NeurIPS), 2023
Paper / Code

Image U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds
Yan Di*, Chenyangguang Zhang*, Ruida Zhang*, Fabian Manhardt, Yongzhi Su, Jason Rambach, Xiangyang Ji, Federico Tombari
International Conference on Computer Vision (ICCV), 2023
Paper / Code

Theme 3: Street Scene Reconstruction
Image Street Gaussians without 3D Object Tracker
Ruida Zhang, Chengxi Li, Chenyangguang Zhang, Xingyu Liu, Haili Yuan, Yanyan Li, Xiangyang Ji, Gim Hee Lee
International Conference on Computer Vision (ICCV), 2025
Paper

Competitions
Image Lessons and Winning Solutions in Industrial Object Detection and Pose Estimation from the 2025 Bin-picking Perception Challenge
Ziqin Huang, Chengxi Li, Yingyue Li, Xingyu Liu, Ruida Zhang, et al.
International Conference on Computer Vision Workshop (ICCVW), 2025
Winner of Bin-picking Perception Challenge 2025 @ ICCV R6D Workshop.
Slides

Image 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.
Slides

Image GDRNPP: Extending Geometry-Guided Direct Regression Network in 2022
Xingyu Liu, Ruida Zhang, Chenyangguang Zhang, Bowen Fu, Jiwen Tang, Xiquan Liang, Jingyi Tang, Xiaotian Cheng, Yukang Zhang, Gu Wang, Xiangyang Ji
European Conference on Computer Vision WorkShop (ECCVW), 2022
Winner of BOP Challenge 2022 @ ECCV R6D Workshop.
Slides / Code