Mingwei Li

李明伟

Ph.D. Student @ Zhejiang University

I am a third-year Ph.D. student at Zhejiang University, advised by Prof. Yi Yang. My research focuses on 3D Computer Vision and Deep Learning, with particular interests in 3D reconstruction, surface normal estimation for transparent objects, and generative models.

Research Interests

3D/4D Reconstruction

Multi-view stereo, Neural Radiance Fields (NeRF), and 3D Gaussian Splatting for high-quality scene reconstruction.

Transparent Object Understanding

Surface normal estimation for transparent and reflective objects using foundation models.

Video Generation

Large-scale video generation models (e.g., Wan2.1) for high-quality video synthesis.

News

2026.01
Accepted BideDPO accepted to ICLR 2026!
2025.07
Accepted TSGS accepted to ACM Multimedia 2025!
2025.05
Accepted DreamRenderer accepted to ICCV 2025!
2023.12
Released Human101 paper and code released on arXiv.

Publications

BideDPO
ICLR 2026

BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment

Dewei Zhou, Mingwei Li, Zongxin Yang, Yu Lu, Yunqiu Xu, Zhizhong Wang, Zeyi Huang, Yi Yang

ICLR 2026

TSGS
ACM MM 2025

TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priors

Mingwei Li, Pu Pang, Hehe Fan, Hua Huang, Yi Yang

ACM Multimedia 2025

DreamRenderer
ICCV 2025

DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models

Dewei Zhou, Mingwei Li, Zongxin Yang, Yi Yang

ICCV 2025

Human101
arXiv 2023

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Mingwei Li, Jiachen Tao, Zongxin Yang, Yi Yang

arXiv 2023

Contact