Biography
I'm a PhD student at Stanford University, advised by Prof. Maneesh Agrawala. Before that, I received my master's degree and bachelor's degree at Zhejiang University, supervised by Prof. Hongzhi Wu. During my master, I'm fortunate to work closely with Dr. Yue Dong, Dr. Xin Tong and Prof. Pieter Peers as a research intern at Microsoft Research Asia and with Prof. Hao Su as a visiting graduate at UC San Diego.
My primary research interests lie in computer graphics and vision, with a focus on developing neural-native graphics pipelines that achieve high quality, scalability, and generalizability. More broadly, I am interested in how visual and geometric representations can serve as foundational components for AI systems that reason about and interact with the visual world.
Recent News
- [2025.09] Started PhD study at Stanford University!
- [2025.05] RenderFormer released! Check out the project page for more details.
- [2025.04] I am honored to receive the Stanford Graduate Fellowship.
- [2025.03] One paper accepted by SIGGRAPH 2025! Stay tuned for more updates!
Publications
Featured publications are highlighted.
Graphics Foundation Models / World Models
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives
Chong Zeng, Yue Dong, Pieter Peers, Lvmin Zhang, Maneesh Agrawala
ECCV, 2026
Extends neural rendering beyond triangles to volumes, environment maps and textured surfaces, scaling past 100k primitives with a render-aware sparse attention.
RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
Chong Zeng, Yue Dong, Pieter Peers, Hongzhi Wu, Xin Tong
SIGGRAPH, 2025
A fully neural rendering pipeline for triangle meshes with global illumination, replacing traditional renderers with a transformer.
Video Generation
TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning
Lvmin Zhang, Shengqu Cai, Muyang Li, Chong Zeng, Beijia Lu, Anyi Rao, Song Han, Gordon Wetzstein, Maneesh Agrawala
ECCV, 2026
A lightweight history embedding for autoregressive video generation, pretrained with randomized frame queries for dense history coverage and then repurposed inside a video diffusion model for content-level consistency.
Object Shape and Appearance Generation
DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
Chong Zeng, Yue Dong, Pieter Peers, Youkang Kong, Hongzhi Wu, Xin Tong
SIGGRAPH, 2024
A novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation.
MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Minghua Liu, Chong Zeng, Xinyue Wei, Ruoxi Shi, Linghao Chen, Chao Xu, Mengqi Zhang, Zhaoning Wang, Xiaoshuai Zhang, Isabella Liu, Hongzhi Wu, Hao Su
NeurIPS (Oral Presentation), 2024
3D native designs enable high-quality reconstruction from multi-view images for 3D object generation.
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion
Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su
CVPR, 2024
Single image to detailed 3D textured mesh in ~1 minute.
Zero123++: A Single Image to Consistent Multi-view Diffusion Base Model
Ruoxi Shi, Hansheng Chen, Zhuoyang Zhang, Minghua Liu, Chao Xu, Xinyue Wei, Linghao Chen, Chong Zeng, Hao Su
arXiv, 2023
An image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view.
Object Shape and Appearance Modeling / Capturing
D-Prism: Differentiable Primitives for Structured Dynamic Modeling
Xingyuan Yu, Yijin Li, Chong Zeng, Yuhang Ming, Hujun Bao, Guofeng Zhang
arXiv, 2026
Extends differentiable primitives to the dynamic domain, binding 3D Gaussians to primitive surfaces so geometry and articulated motion are modeled jointly.
GS^3: Efficient Relighting with Triple Gaussian Splatting
Zoubin Bi, Yixin Zeng, Chong Zeng, Fan Pei, Xiang Feng, Kun Zhou, Hongzhi Wu
SIGGRAPH Asia, 2024
Relightable Gaussian splatting representation for real-time & high-quality relighting.
NRHints: Relighting Neural Radiance Fields with Shadow and Highlight Hints
Chong Zeng, Guojun Chen, Yue Dong, Pieter Peers, Hongzhi Wu, Xin Tong
SIGGRAPH, 2023
Relightable neural radiance field that models full light transport effects, with shadow and highlight hints helping with high-frequency effects.
A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance
Xianmin Xu, Yuxin Lin, Haoyang Zhou, Chong Zeng, Yaxin Yu, Kun Zhou, Hongzhi Wu
CVPR, 2023
A unified structured light for high-quality acquisition of both shape and reflectance from a single view.
DiFT: Differentiable Differential Feature Transform for Multi-View Stereo
Kaizhang Kang, Chong Zeng, Hongzhi Wu, Kun Zhou
arXiv, 2022
Transform the differential cues from a stack of images into spatially discriminative and view-invariant per-pixel features for MVS.
Performance Optimization
Critique of 'productivity, Portability, Performance: Data-Centric Python' by SCC Team From Zhejiang University
Zihan Yang, Yi Chen, Kaiqi Chen, Xingjian Qian, Shaojun Xu, Yun Pan, Chong Zeng, Jianhai Chen, Yin Zhang, Zeke Wang
TPDS, 2023
Reproduce CPU / GPU / distributed computing performance of DaCe (Data-Centric Python) on Azure.
Calculation and optimization of correlation function in distillation method of lattice quantum chromodynamcis (in Chinese)
Ren-Qiang Zhang, Xiang-Yu Jiang, Yu Jiong-Chi, Chong Zeng, Ming Gong, Shun Xu
Acta Physica Sinica, 2021
Accelerate lattice quantum chromodynamcis calculation using MPI, OpenMP, and SIMD.
Engineering Projects
ZJU Mirror
Project Leader
ZJU's new open source software mirror site. I worked as the project leader, and also participated in front-end development and all back-end manager development.
ZJU Git
Project Leader
ZJU's new Git service. I worked as the project leader, helped deploy and maintain this platform for all students and faculty in ZJU.
Education & Experience
PhD Student
Stanford University, Sep 2025 - Present
Research Intern
NVIDIA Research, Jun 2026 - Present
- Autoregressive Streaming Video Generation / Generative Rendering
Visiting Graduate
UC San Diego, Nov 2023 - Apr 2024
- 3D Digital Object Asset Generation
Research Intern
Microsoft Research Asia, Oct 2022 - June 2023
- Neural Relighting Research with NeRF Scene Representation and Diffusion Models
Research Assistant
State Key Lab of CAD&CG, Zhejiang University, March 2021 - July 2022
- Differentiable Appearance and Geometry Acquisition
Research Intern
Microsoft Research Asia, July 2021 - Oct 2021
- Performance Acceleration for Large Scale Real-Time Graphics Super-Resolution Neural Networks
Academic Service
Conference Reviewer
- ICLR
- NeurIPS
- ICML
- SIGGRAPH
- SIGGRAPH Asia
- Eurographics
- CVPR
- ECCV
- AAAI
- ACM MM
Journal Reviewer
- ACM TOG
- IEEE TVCG
- IEEE TPAMI