About Me
Postdoc at the Geometric Computation group led by Prof. Leonidas Guibas in Stanford. Research interests include 3D graphics, 3D computer vision and robotics.
Interested in new and cool things, and wanted to figure out everything beneath a particular technique. Feel free to contact me at yangyou at stanford.edu if you have any question about my research or want to have a broad discussion in the field of 3D understanding. Including your biography when seeking a discussion would be highly appreciated.
News
2025.01: Our paper: Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning is accepted to ICLR 2025! [Paper] [Code] [Huggingface Demo]
2025.01: Our paper: Make a Donut: Language-Guided Hierarchical EMD-Space Planning for Zero-shot Deformable Object Manipulation is accepted to IEEE Robotics and Automation Letters (RA-L)! [Paper] [Code (Coming soon)] [Project Page]
2024.10: Our paper: ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process is accepted to NeurIPS 2024! [Paper] [Project Page]
2024.07: Our paper: PACE: Pose Annotations in Cluttered Environments is accepted to ECCV 2024! [Paper] [Code] [Project Page]
2024.07: Our paper: Bridging the Gap Between Human Motion and Action Semantics via Kinematics Phrases is accepted to ECCV 2024! [Paper] [Project Page]
2024.06: Our paper: RPMArt: Towards Robust Perception and Manipulation for Articulated Objects is accepted to IROS 2024! [Paper] [Code] [Project Page]
2024.06: Our paper: CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation is accepted to TPAMI 2024! This is perhaps the most generalizable category-level pose estimation method you can find, and it only requires cheap synthetic data for training! [Paper] [Code] [Project Page]
2024.01: Our paper: SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation is accepted to ICLR 2024! [Paper] [Code]
2023.12: Our paper: Primitive-based 3D Human-Object Interaction Modelling and Programming is accepted to AAAI 2024! [Paper] [Code]
2023.03: Our paper: CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame is accepted to AAAI 2023 Oral! [Paper] [Code]
2022.03: Our paper: UKPGAN: A General Self-Supervised Keypoint Detector is accepted to CVPR 2022! [Paper] [Code] [Project Page]
2022.03: Our paper: Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes is accepted to CVPR 2022! [Paper] [Code] [Project Page]
2022.03: Our paper: CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild is accepted to CVPR 2022! [Paper] [Code] [Project Page]
2021.11: Our paper: PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features is accepted to TPAMI, and to appear in the upcoming issues! [Paper] [Code] [Project Page]
2021.04: Our paper: Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine is accepted to TPAMI, and to appear in the upcoming issues! [Paper] [Project Page]
2021.02: Our paper Skeleton Merger: an Unsupervised Aligned Keypoint Detector is accepted as CVPR 2021 Oral! [Paper] [Code]
2020.02: Our paper KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations is accepted to CVPR 2020! [Paper] [Code] [Project Page]