Puhua Jiang — Researcher in 3D Vision & Graphics

About

I am currently a Researcher at Tencent Hunyuan, working on 3D computer vision and graphics.

Prior to this, I obtained my Ph.D. degree from Tsinghua University, where I was fortunate to be supervised by Prof. Ruqi Huang. I received my M.S. degree in Computer Vision from the University of Michigan. During COVID-19, I worked as a research assistant at Tsinghua University under Prof. Lu Fang. I received my B.S. degree from Huazhong University of Science and Technology in 2019.

3D Generation & Reconstruction

Neural rendering (NeRF, 3D Gaussian splatting), multi-view reconstruction and 3D asset generation.

3D Animation

Automatic rigging, skinning, and motion generation for articulated characters.

Geometric Shape Analysis

Non-rigid shape matching, functional maps and point cloud registration.

News

Sep 2026 PaperOne paper was accepted by CGF 2026.
May 2026 PaperOne paper was accepted by SIGGRAPH 2026. project page
Nov 2025 PaperOne paper was accepted by ICLR 2026.
Nov 2025 PaperOne paper was accepted by 3DV 2026.
Sep 2025 PaperOne paper was accepted by NeurIPS 2025.
Feb 2025 PaperTwo papers were accepted by CVPR 2025.
Jul 2024 PaperOne paper was accepted by SIGGRAPH 2024.
Sep 2023 PaperOne paper was accepted by NeurIPS 2023.
Jul 2023 PaperOne paper was accepted by ICCV 2023.
May 2023 PaperOne paper was accepted by ENGINEERING.
Feb 2023 PaperOne paper was accepted by CVPR 2023.
Jul 2022 ServiceServing as the teaching assistant for GAMES204 — Computational Photography streamed on Bilibili.
Mar 2021 ServiceServing as the student organizer in the GigaVision Challenge.
Jul 2020 WorkStarting an internship as a computer vision R&D engineer at Baidu.

Publications

Selected work on 3D vision, graphics and geometric learning.

NFR: Neural Feature-Guided Non-Rigid Shape Registration

Zhangquan Chen†, Puhua Jiang†, Mingze Sun†, Ruqi Huang

CGF Computer Graphics Forum (CGF), 2026

PDF

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

Zijie Wu, Lixin Xu, Puhua Jiang, Sicong Liu, Chunchao Guo, Xiang Bai

SIGGRAPH ACM SIGGRAPH (SIGGRAPH), 2026

PDF Project Code

Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization

Zhejia Cai†, Puhua Jiang†, Shiwei Mao, Hongkun Cao, Ruqi Huang

3DV International Conference on 3D Vision (3DV), 2026

PDF

Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization

Jingfeng Guo, Jian Liu, Jinnan Chen, Shiwei Mao, Changrong Hu, Puhua Jiang, Junlin Yu, Jing Xu, Qi Liu, Lixin Xu, Zhuo Chen, Chunchao Guo

NeurIPS Conference on Neural Information Processing Systems (NeurIPS), 2025

PDF Code

DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation

Junhao Chen, Mingjin Chen, Jianjin Xu, Xiang Li, Junting Dong, Mingze Sun, Puhua Jiang, Hongxiang Li, Yuhang Yang, Hao Zhao, Xiaoxiao Long, Ruqi Huang

arXiv arXiv preprint, 2025

PDF Project Code

Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation

Hunyuan Team

arXiv arXiv preprint, 2025

PDF

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels

Hunyuan Team

arXiv arXiv preprint, 2025

PDF Code

DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features

Zhangquan Chen†, Puhua Jiang†, Ruqi Huang

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2025

PDF Code

DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters

Mingze Sun, Junhao Chen, Junting Dong, Yurun Chen, Xinyu Jiang, Shiwei Mao, Puhua Jiang, Jingbo Wang, Bo Dai, Ruqi Huang

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2025

PDF Code

SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation

Mingze Sun†, Chen Guo†, Puhua Jiang†, …, Ruqi Huang

SIGGRAPH Asia SIGGRAPH Asia, 2024

Non-Rigid Shape Registration via Deep Functional Maps Prior

Puhua Jiang, Mingze Sun, Ruqi Huang

NeurIPS Conference on Neural Information Processing Systems (NeurIPS), 2023

PDF Code

Spatially and Spectrally Consistent Deep Functional Maps

Mingze Sun, Shiwei Mao, Puhua Jiang, Maks Ovsjanikov, Ruqi Huang

ICCV International Conference on Computer Vision (ICCV), 2023

PDF Code

Neural Intrinsic Embedding for Non-Rigid Point Cloud Matching

Puhua Jiang, Mingze Sun, Ruqi Huang

CVPR Conference on Computer Vision and Pattern Recognition (CVPR), 2023

PDF Code

Group Interaction Field for Learning and Explaining Pedestrian Anticipation

Xueyang Wang†, Xuecheng Chen†, Puhua Jiang†, Haozhe Lin†, Xiaoyun Yuan, Mengqi Ji, Yuchen Guo, Ruqi Huang, Lu Fang

ENGINEERING ENGINEERING, 2023

PDF Code

Education

Ph.D. in Computer Science · Tsinghua University

Supervised by Prof. Ruqi Huang

2021 — 2025
M.S. in Electrical & Computer Engineering · University of Michigan, Ann Arbor

Computer Vision

2019 — 2021
B.S. in Automation · Huazhong University of Science and Technology

2015 — 2019

Service

Teaching Assistant

Computational Photography

Tsinghua University

Spring 2023
Digital Image and Video Processing

Tsinghua University

Fall 2022
GAMES204 — Computational Photography

GAMES

Summer & Fall 2022
Computational Photography

Tsinghua University

Spring 2022
Digital Image and Video Processing

Tsinghua University

Fall 2021