Peng-Shuai Wang (王鹏帅)

Assistant Professor, Ph.D. Advisor
Wangxuan Institute of Computer Technology
Peking University

Address: Haidian District, Beijing, China
Email: wangps AT hotmail.com

Biography

I am a tenure-track Assistant Professor at Peking University from 2022. I am now working closely with top graphics labs at Peking University led by Prof. Baoquan Chen, Prof. Zhouhui Lian, and Prof. Guoping Wang. Before joining Peking University, I was a senior researcher in the graphics group at Microsoft Research Asia led by Dr. Xin Tong, where I was also a research intern from 2014 to 2018, mentored by Dr. Yang Liu. I received my Ph.D. from the Institute for Advanced Study at Tsinghua University in 2018, supervised Prof. Baining Guo. I got my Bachelor's degree from the Department of Automation at Tsinghua University in 2013.

My research interests include computer graphics, geometry processing, and deep learning. My recent research forcus is to develop a unified 3D deep learning framework for the understanding, generation, and rendering of 3D data. My paper on Octree-based 3D Convolutional Neural Networks is one of the Top-5 Most Cited Papers in ACM Transactions on Graphics from 2017 to 2022. I have been awarded the AsiaGraphics Young Researcher Award and the AI 2000 Most Influential Scholar Award Honorable Mention in recognition of my contributions to the field of computer graphics from 2012 to 2024.

I am always actively recruiting Ph.D. students and research interns! Welcome to contact me with your CV and research statement!

News

  • Oct. 25, 2024: I have 1 paper accepted by Computational Visual Media (CVMJ).
  • Aug. 01, 2024: I have 1 paper conditionally accepted by SIGGRAPH Asia 2024 (Journal Track).
  • Apr. 24, 2024: Our paper SDF-StyleGAN is awarded one of the Top-10 Most Cited Papers in CGF from 2022 to 2023.
  • Feb. 28, 2024: I have 4 papers accepted recently, by CVPR, ICLR, CVMJ, and TVCG, respectively.
  • Oct. 15, 2023: I am awarded the AsiaGraphics Young Researcher Award.
  • Aug. 04, 2023: I have 3 papers conditionally accepted by SIGGRAPH Asia 2023.
  • Mar. 25, 2023: I have 2 papers conditionally accepted by SIGGRAPH 2023, including one single-author paper.

Selected Publications

OctFusion: Octree-based Diffusion Models for 3D Shape Generation
Bojun Xiong*, Si-Tong Wei*, Xin-Yang Zheng, Yan-Pei Cao, Zhouhui Lian, and Peng-Shuai Wang (*Joint first authors)
Technical Report, 2024
Code Arxiv
Joint Point Cloud Upsampling and Cleaning with Octree-based CNNs
Jihe Li, Bo Pang, and Peng-Shuai Wang
Computational Visual Media (CVMJ), 2024
Code Arxiv
Neural Laplacian Operator for 3D Point Clouds
Bo Pang, Zhongtian Zheng, Yilong Li, Guoping Wang, and Peng-Shuai Wang
ACM Transactions on Graphics (SIGGRAPH Asia), 43(6), 2024
Code Arxiv
Point Transformer V3: Simpler, Faster, Stronger
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, and Hengshuang Zhao
Computer Vision and Pattern Recognition (CVPR), 2024 - (Oral, 0.78% acceptance rate)
Code Arxiv
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
Siming Yan, Yu-Qi Yang, Yu-Xiao Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, and Qixing Huang
International Conference on Learning Representations (ICLR), 2024
Code Arxiv
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding
Yu-Qi Yang, Yu-Xiao Guo, Jian-Yu Xiong, Yang Liu, Hao Pan, Peng-Shuai Wang, Xin Tong, and Baining Guo
Computational Visual Media (CVMJ), 2024
Code Arxiv Project
Learning the Geodesic Embedding with Graph Neural Networks
Bo Pang*, Zhongtian Zheng*, Guoping Wang, and Peng-Shuai Wang (*Joint first authors)
ACM Transactions on Graphics (SIGGRAPH Asia), 42(6), 2023
Code Slides Arxiv
Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian
Zixiong Wang, Yunxiao Zhang, Rui Xu, Fan Zhang, Peng-Shuai Wang, Shuangmin Chen, Shiqing Xin, Wenping Wang, and Changhe Tu
ACM Transactions on Graphics (SIGGRAPH Asia), 42(6), 2023
Code Arxiv
SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images
Guo Pu, Peng-Shuai Wang, and Zhouhui Lian
SIGGRAPH Asia (Conference track), 2023
Code Arxiv
Randomized Quantization for Data Agnostic Representation Learning
Huimin Wu*, Chenyang Lei*, Xiao Sun, Peng-Shuai Wang, Qifeng Chen, Kwang-Ting Cheng, Stephen Lin, and Zhirong Wu (*Joint first authors)
International Conference on Computer Vision (ICCV), 2023
Code Arxiv
Neural-IMLS: Learning Implicit Moving Least-Squares for Surface Reconstruction from Unoriented Point clouds
Zixiong Wang, Pengfei Wang, Peng-Shuai Wang, Qiujie Dong, Junjie Gao, Shuangmin Chen, Shiqing Xin, Changhe Tu, and Wenping Wang
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023
Code Arxiv
OctFormer: Octree-based Transformers for 3D Point Clouds
Peng-Shuai Wang
ACM Transactions on Graphics (SIGGRAPH), 42(4), 2023
Code Slides Arxiv Project
Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
Xin-Yang Zheng, Hao Pan, Peng-Shuai Wang, Xin Tong, Yang Liu, and Heung-Yeung Shum
ACM Transactions on Graphics (SIGGRAPH), 42(4), 2023
Code Slides Arxiv Project
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
Xin-Yang Zheng, Yang Liu, Peng-Shuai Wang, and Xin Tong
Computer Graphics Forum (SGP), 2022
Code Arxiv Project
Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
Peng-Shuai Wang, Yang Liu, and Xin Tong
ACM Transactions on Graphics (SIGGRAPH), 41(4), 2022
Code Code (Stale) Slides Arxiv Project
Semi-Supervised 3D Shape Segmentation with Multilevel Consistency and Part Substitution
Chun-Yu Sun, Yu-Qi Yang, Hao-Xiang Guo, Peng-Shuai Wang, Xin Tong, Yang Liu, and Heung-Yeung Shum
Computational Visual Media (CVMJ), 2022
Code Arxiv Project
Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks
Yu-Qi Yang, Peng-Shuai Wang, and Yang Liu
International Conference on Computer Vision (ICCV), 2021
Code Arxiv Project
Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
Peng-Shuai Wang, Yang Liu, Yu-Qi Yang, and Xin Tong
International Joint Conferences on Artificial Intelligence (IJCAI), 2021
Code Slides Arxiv Project
Deep Implicit Moving Least-Squares Functions for 3D Reconstruction
Shi-Lin Liu, Hao-Xiang Guo, Hao Pan, Peng-Shuai Wang, Xin Tong, and Yang Liu
Computer Vision and Pattern Recognition (CVPR), 2021
Code Arxiv
OctSurf: Efficient hierarchical voxel-based molecular surface representation for protein-ligand affinity prediction
Qinqing Liu , Peng-Shuai Wang, Chunjiang Zhu, Blake Blumenfeld Gaines, Tan Zhu, Jinbo Bi, and Minghu Song
Journal of Molecular Graphics and Modelling, 2021
Jeffry D. Madura Memorial Graphics Prize
Code Paper
Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
Peng-Shuai Wang, Yu-Qi Yang, Qian-Fang Zou, Zhirong Wu, Yang Liu, and Xin Tong
AAAI Conference on Artificial Intelligence (AAAI), 2021
Code Slides Arxiv Project
Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion
Peng-Shuai Wang, Yang Liu, and Xin Tong
Computer Vision and Pattern Recognition (CVPR) Workshops, 2020
Code Arxiv
Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes
Peng-Shuai Wang, Chun-Yu Sun, Yang Liu and Xin Tong
ACM Transactions on Graphics (SIGGRAPH Asia), 37(6), 2018
Code Slides Arxiv Project DOI
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong
ACM Transactions on Graphics (SIGGRAPH), 36(4), 2017
Top-5 Most Cited Papers in ACM Transactions on Graphics from 2017 to 2022
Code Code (Stale) Slides Arxiv Project DOI
Mesh Denoising via Cascaded Normal Regression
Peng-Shuai Wang, Yang Liu, and Xin Tong
ACM Transactions on Graphics (SIGGRAPH Asia), 35(6), 2016
Code Data Project DOI
Rolling Guidance Normal Filter for Geometric Processing
Peng-Shuai Wang, Xiao-Ming Fu, Yang Liu, Xin Tong, Shi-Lin Liu, and Baining Guo
ACM Transactions on Graphics (SIGGRAPH Asia), 34(6), 2015
EXE Data Video DOI

Teaching

  • Computer Vision (Undergraduate course, 2023/2024 Fall)
  • Programming in Artificial Intelligence (Undergraduate course, 2023/2024 Fall)
  • The Frontiers of Geometry Computing (Undergraduate course, 2023/2024 Spring)

Team

  • Graduate Students in my lab:
    Rui-Huan Wang (Ph.D. student, Peking University, 2025)
    Si-Tong Wei (Ph.D. student, Peking University, 2024)
    Jun-Hao Wang (Ph.D. student, Peking University, 2024)
  • Research Interns closely collaborating with me for more than 6 months:
    Bo Pang (Ph.D. student, Peking University, 2022/10 - now)

    Xiang Wang (Undergraduate, Peking University, 2023/04 - 2024/05)
    Jihe Li (Master's student, Peking University, 2023/05 - 2024/03)
    Bojun Xiong (Master's student, Peking University, 2023/05 - 2024/05)
    Zhongtian Zheng (Master's student, Peking University, 2022/10 - 2024/05)
    Xin-Yang Zheng (Ph.D. student, Tsinghua University, 2021/07 - 2023/01)
    Yu-Qi Yang (Ph.D. student, Tsinghua University, 2021/01 - 2022/02)

Services

  • Associate Editor: Computers & Graphics
  • Program Committee: SIGGRAPH Asia 2024, Eurographics 2024/2025, SGP 2024/2025, CVM 2023-2025, GMP 2024/2025, SMI 2021-2025, GDC 2022/2023, CADCG 2023/2024, CGI 2023, 3DV 2020
  • Paper Reviewer: SIGGRAPH, SIGGRAPH Asia, TOG, TVCG, Pacific Graphics, Eurographics, CGF, Computers & Graphics, CAD, CAG-D, TIP, TPAMI, IJCV, CVPR, ICCV, ECCV

Awards