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 third-year Ph.D. student in computer science at Stanford University advised by Leonidas Guibas. My research interests include 3D computer vision, computer graphics, and geometric computing. I am particularly interested in developing and leveraging better data representations in 3D shape analysis and processing.

I had the pleasure of collaborating with Kostas Daniilidis (UPenn) and Jeannette Bohg. I also did a rotation with Jiajun Wu in Spring 2021 and an internship with Ron Fedkiw in Summer 2019 through the UGVR program. 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


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)
ArXiv preprint, 2023
Paper | Project | Video
teaser_nap NAP: Neural 3D Articulation Prior
Jiahui Lei, Congyue Deng, Bokui Shen, Leonidas Guibas, Kostas Daniilidis
ArXiv preprint, 2023
Paper | Project | Video
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_alt_conv_lstm Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Congyue Deng, Tai-Jiang Mu, Shi-Min Hu
ArXiv preprint, 2020
Paper | BibTex
teaser_adversarial_tradeoff Towards Understanding the Trade-off Between Accuracy and Adversarial Robustness
Congyue Deng*, Yi Tian* (*equal contributors)
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: SIGGRAPH (2022, 2023), CVPR (2022, 2023), ICCV (2023), ECCV (2022), ICML(2022, 2023), NeurIPS (2022, 2023), ICRA (2023), AAAI (2023), 3DV(2022), ICIG (2021)

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

stanford_logo 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.