Congyue Deng

Ph.D. Student, Geometric Computing Group
Department of Computer Science, Stanford University

Email: congyue [at] stanford [dot] edu
Office: 239 Gates Computer Science Building

profile photo profile photo

I am a forth-year Ph.D. student in computer science at Stanford University advised by Leonidas Guibas. My research interests include 3D computer vision and geometric deep learning. I am particularly interested in developing and leveraging better data representations in 3D shape analysis and processing. I also had the pleasure of collaborating with Kostas Daniilidis (UPenn) and Jeannette Bohg. I obtained my B.S. in mathematics from Tsinghua University in 2020 with a GPA ranking 1/114.
"The reality of the universe is geometrical."    -- E. A. Burtt. The Metaphysical Foundations of Modern Physical Science

"A scientific theory is usually felt to be better than its predecessors not only in the sense that it is a better instrument for discovering and solving puzzles but also because it is somehow a better representation of what nature is really like."    -- Thomas Kuhn. The Structure of Scientific Revolutions

Research

teaser_feat_consensus Zero-Shot Image Feature Consensus with Deep Functional Maps
Xinle Cheng, Congyue Deng, Adam Harley, Yixin Zhu, Leonidas Guibas (corresponding author)
ArXiv preprint
Paper | BibTex
teaser_linerf Rethinking Directional Integration in Neural Radiance Fields
Congyue Deng, Jiawei Yang, Leonidas Guibas, Yue Wang
ArXiv preprint
Paper | Project | Video | BibTex
teaser_sparsedff SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
Qianxu Wang, Haotong Zhang, Congyue Deng, Yang You, Hao Dong, Yixin Zhu, Leonidas Guibas (corresponding author)
International Conference on Learning Representations (ICLR), 2024
Paper | Code | Project | BibTex
teaser_donut Make a Donut🍩: Hierarchical EMD-Space Planning for Zero-shot Deformable Manipulation with Tools
Yang You, Bokui Shen, Congyue Deng, Haoran Geng, Songlin Wei, He Wang, Leonidas Guibas
ArXiv preprint
Paper | BibTex
teaser_equivact EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation
Jingyun Yang*, Congyue Deng*, Jimmy Wu, Rika Antonova, Leonidas Guibas, Jeannette Bohg (*equal contribution)
IEEE International Conference on Robotics and Automation (ICRA), 2024
Paper | Project | Video | BibTex
teaser_sage SAGE🌿: Bridging Semantic and Actionable Parts for Generalizable Manipulation of Articulated Objects
Haoran Geng*, Songlin Wei*, Congyue Deng, Bokui Shen, He Wang, Leonidas Guibas (*equal contribution, equal advising)
Robotics: Science and Systems (RSS), 2024
Paper | Project | Video | BibTex
teaser_banana Banana🍌: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
Congyue Deng*, Jiahui Lei*, Bokui Shen, Kostas Daniilidis, Leonidas Guibas (*equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), 2023 Spotlight
Paper | Project | Video | BibTex
teaser_nap NAP😴: Neural 3D Articulation Prior
Jiahui Lei, Congyue Deng, Bokui Shen, Leonidas Guibas, Kostas Daniilidis
Advances in Neural Information Processing Systems (NeurIPS), 2023
Paper | Code | Project | Video | BibTex
teaser_efem EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
Jiahui Lei, Congyue Deng, Karl Schmeckpeper, Leonidas Guibas, Kostas Daniilidis
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
Paper | Code | Dataset | Project | Video | BibTex
teaser_nerdi NeRDi🤓: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Congyue Deng, Chiyu "Max" Jiang, Charles R. Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
Paper | Video | BibTex
teaser_progrip Unsupervised Learning of Shape Programs with Repeatable Implicit Parts
Boyang Deng*, Sumith Kulal*, Zhengyang Dong, Congyue Deng, Yonglong Tian, Jiajun Wu (*equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), 2022
Paper | Project | Video | BibTex
teaser_vector_neurons Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Congyue Deng, Or Litany, Yueqi Duan, Adrien Poulenard, Andrea Tagliasacchi, Leonidas Guibas
International Conference on Computer Vision (ICCV), 2021 Oral
Paper | Code | Project | Video | Short Video | BibTex
teaser_adversarial_tradeoff Towards Understanding the Trade-off Between Accuracy and Adversarial Robustness
Congyue Deng*, Yi Tian* (*equal contribution)
ICML workshop on the Security and Privacy of Machine Learning, 2019
Manuscript | Poster

teaser_lofted_shapes Interactive Modeling of Lofted Shapes from a Single Image
Congyue Deng, Jiahui Huang, Yong-Liang Yang
Computational Visual Media (CVM), 2019: 1-11
Paper | BibTex


Professional Services
Conference reviewer: CVPR (2022, 2023, 2024), ICCV (2023), ECCV (2022, 2024), SIGGRAPH (2022, 2023, 2024), SIGGRAPH Asia (2023), ICML (2022, 2023, 2024), NeurIPS (2022, 2023), ICRA (2023), ICLR (2024), AAAI (2023, 2024), 3DV(2022, 2024), CPAL (2024), ICIG (2021)

Journal reviewer: TVCG, TPAMI, IJRR, Computer Graphics Forum, Computers & Graphics

Teaching
stanford_logo Teaching Assistant, Computer Vision, From 3D Perception to 3D Reconstruction and beyond (CS231A), Spring 2024

Teaching Assistant, Computer Graphics in the Era of AI (CS348I), Winter 2024

Guest Lecturer, Neural Representations and Generative Models for 3D Geometry (CS348n), Winter 2022, Spring 2023
tsinghua_logo Teaching Assistant, Combinatorics and Algorithm Design (70240384), Fall 2019

Teaching Assistant, Combinatorics (60240013), Fall 2019

Volunteer Tutor and Counselor at the Student Learning and Development Center

Website design from Jon Barron, source code here.