Zhihao Li (ζŽζ™Ίζ˜Š)

Co-Founder & CEO, SparcAI Inc.
PhD, Nanyang Technological University, Singapore

E-mail: zhihao.li [AT] sparclab.ai

Google Scholar    /    GitHub

About me

I'm the Co-Founder & CEO of SparcAI Inc., building next-generation foundation models for 3D generation and world modeling. I received my PhD from Nanyang Technological University, supervised by Prof. Bihan Wen, and my bachelor's and master's degrees from Nanjing University.

My research interests lie in 3D generation, video generation, world models, and data compression.

News

  • [2026] RF4D is accepted by CVPR 2026!
  • [2025] Sparc3D is accepted by NeurIPS 2025!
  • [Sep 26, 2024] Two papers are accepted by NeurIPS 2024!
  • [July 1, 2024] A paper is accepted by ECCV 2024!
  • [May 2, 2024] A paper is accepted by ICML 2024!
  • [Jan 18, 2024] A paper is accepted by T-PAMI!

Honors and Awards

Publications

Topics: / / / / /

(* represents the equal contribution.)
NeurIPS'25   Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling
Zhihao Li, Yufei Wang, Heliang Zheng, Yihao Luo, Bihan Wen
Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
Homepage / Paper / Demo / Video

CVPR'26   RF4D: Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes
Jiarui Zhang, Zhihao Li, Chong Wang, Bihan Wen
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Homepage / Paper

Arxiv'25   Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Yufei Wang, Lanqing Guo, Zhihao Li, Jiaxing Huang, Pichao Wang, Bihan Wen, Jian Wan
ICCV, 2025
Paper / Code

NeurIPS'24   From Chaos to Clarity: 3DGS in the Dark
Zhihao Li*, Yufei Wang*, Alex C. Kot, Bihan Wen
Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Paper

NeurIPS'24   ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Mode
Yufei Wang, Zhihao Li, Lanqing Guo, Wenhan Yang, Alex C. Kot, Bihan Wen
Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Paper / Code

ECCV'24   Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
Zixuan Fu, Lanqing Guo, Chong Wang, Yufei Wang, Zhihao Li, Bihan Wen
The European Conference on Computer Vision (ECCV), 2024
Paper / Code

ICML'24   Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach
Zhihao Li*, Yufei Wang*, Alex C. Kot, Bihan Wen
International Conference on Machine Learning (ICML), 2024
Homepage / Paper

T-PAMI'24   Efficient Visual Computing with Camera RAW Snapshots
Zhihao Li, Ming Lu, Xu Zhang, Xin Feng, M. Salman Asif, Zhan Ma
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024
Homepage / Paper / Code

ICASSP'24   Token-based Spatiotemporal Representation of the Events
Bin Jiang*, Zhihao Li*, M. Salman Asif, Xun Cao, Zhan Ma
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024 (Oral)
Paper / Code

CVPRW'22   Rendering Nighttime Image Via Cascaded Color and Brightness Compensation
Zhihao Li, Si Yi, Zhan Ma
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2022
Paper / Code

ICMV'20   Robust white balance estimation using joint attention and angular loss optimization
Zhihao Li, Zhan Ma
International Conference on Machine Vision (ICMV), 2020
Paper

Asilomar'20   In-Camera Raw Compression: A New Paradigm from Image Acquisition to Display
Zhihao Li, Haojie Liu, Lin Yang, Zhan Ma
Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2020
Paper

Professional Service

  • Journal reviewer: TCSVT, TNNLS
  • Conference reviewer: NeurIPS, CVPR, ICCV, ICML, ICLR, AISTATS, ECCV, ICME