Jiahui Huang

Jiahui Huang

Research Scientist

Nice to meet you.

I am currently a research scientist at NVIDIA Toronto AI Lab led by Sanja Fidler. I received my Ph.D. in 2023 from the Graphics and Geometric Computing Group at Tsinghua University, China, advised by Shi-Min Hu. I was also a visiting researcher in the Geometric Computing group at Stanford University, led by Leonidas Guibas. My primary research interest lies in the joint field of 3D computer vision and graphics, including neural reconstruction, dynamic scene perception, and SLAM.

⛵️ We are actively looking for interns to work with at NVIDIA Research. Please reach out to me if you are interested in the position.

This page was last updated in Oct 2024.

Interests
  • 3D Computer Vision
  • Computer Graphics
  • Machine Learning
Education

  • PhD in Computer Science, 2018 - 2023

    Tsinghua University

  • BEng in Computer Science, 2014 - 2018

    Tsinghua University

Selected Publications

See Full List

SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
NeurIPS 2024
Xuanchi Ren, Yifan Lu, Hanxue Liang, Jay Zhangjie Wu, Huan Ling, Mike Chen, Sanja Fidler, Francis Williams, Jiahui Huang
PDF Project
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
OmniRe: Omni Urban Scene Reconstruction
ArXiv 2024
Ziyu Chen, Jiawei Yang, Jiahui Huang, Riccardo De Lutio, Janick Martinez Esturo, Boris Ivanovic, Or Litany, Zan Gojcic, Sanja Fidler, Marco Pavone, Li Song, Yue Wang
PDF Code Project
OmniRe: Omni Urban Scene Reconstruction
fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
SIGGRAPH 2024
Francis Williams, Jiahui Huang, Jonathan Swartz, Gergely Klár, Vijay Thakkar, Matthew Cong, Xuanchi Ren, Ruilong Li, Clement Fuji-Tsang, Sanja Fidler, Eftychios Sifakis, Ken Museth
PDF Code Video
fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
Computer Vision and Pattern Recognition (CVPR) 2024 - Highlight
Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams
PDF Project Video
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
International Conference on Computer Vision (ICCV) 2023
PDF Project
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion
Neural Kernel Surface Reconstruction
Computer Vision and Pattern Recognition (CVPR) 2023 - Highlight
PDF Code Project Video
Neural Kernel Surface Reconstruction
A Neural Galerkin Solver for Accurate Surface Reconstruction
SIGGRAPH Asia 2022
Jiahui Huang, Hao-Xiang Chen, Shi-Min Hu
PDF Code Video
A Neural Galerkin Solver for Accurate Surface Reconstruction
Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
T-PAMI 2022
PDF Code Project
Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
Computer Vision and Pattern Recognition (CVPR) 2021 - Oral
Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas J. Guibas
PDF Cite Code Dataset
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
Computer Vision and Pattern Recognition (CVPR) 2021
Jiahui Huang, Shi-Sheng Huang, Haoxuan Song, Shi-Min Hu
PDF Cite Code Video
DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
WallNet: Reconstructing General Room Layouts from RGB Images
Graphical Models 2020
Jiahui Huang, Zheng-Fei Kuang, Fang-Lue Zhang, Tai-Jiang Mu
PDF Cite
WallNet: Reconstructing General Room Layouts from RGB Images
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
Computer Vision and Pattern Recognition (CVPR) 2020
Jiahui Huang, Sheng Yang, Tai-Jiang Mu, Shi-Min Hu
PDF Cite Code Slides Video
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation
International Conference on Computer Vision (ICCV) 2019
Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu
PDF Cite Dataset
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation
DeepPrimitive: Image decomposition by layered primitive detection
Computational Visual Media (CVM) 2018
Jiahui Huang, Jun Gao, Vignesh Ganapathi-Subramanian, Hao Su, Yin Liu, Chengcheng Tang, Leonidas J. Guibas
PDF Cite
DeepPrimitive: Image decomposition by layered primitive detection

Projects

3-Sweep: Extracting Editable Objects from a Single Photo
3-Sweep is a creative method for 3D modeling from a single image, which is proposed in a SIGGRAPH ASIA 2013 paper by Tsinghua University, Tel Aviv University and The Interdisciplinary Center. According to many readers’ requests, I re-implemented and released this software.
3-Sweep: Extracting Editable Objects from a Single Photo

Contact