I am currently a 3rd-Year Master student at Tsinghua University, under the guidance of Prof. Haoqian Wang. I got B.Eng. degree in Measurement and control technology and instruments at Southeast University. During my study in Tsinghua University, I spent a good time with Prof. Yebin Liu and Prof. Hanspeter Pfister.

Currently, my research topic is 3D computer vision, with a particular focus on 3D scene and 3D human reconstruction. (e.g. NeRF, 3D-GS)

github / google scholar / cv

๐Ÿ”ฅ News

  • 2024.02: ย ๐ŸŽ‰๐ŸŽ‰ 2 paper accepted to ECCV 2024 !!!
  • 2024.02: ย ๐ŸŽ‰๐ŸŽ‰ LangSplat has been selected as CVPR 2024 Highlight !!!
  • 2024.02: ย ๐ŸŽ‰๐ŸŽ‰ 1 paper accepted to CVPR 2024 !!!
  • 2023.11: ย ๐ŸŽ‰๐ŸŽ‰ 1 paper accepted to AAAI 2024 !!!

๐Ÿ“ Publications

CVPR 2024 Highlight
sym

LangSplat: 3D Language Gaussian Splatting

Minghan Qin*, Wanhua Li*โ€ , Jiawei Zhou*, Haoqian Wangโ€ , Hanspeter Pfister

WEBSITE

  • We introduces LangSplat, which constructs a 3D language field that enables precise and efficient open-vocabulary querying within 3D spaces.
ECCV 2024
sym

Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections

Dongbin Zhang*, Chuming Wang*, Weitao Wang, Peihao Li, Minghan Qin, Haoqian Wangโ€ 

Website

  • We utilize 3D Gaussian Splatting with introduced separated intrinsic and dynamic appearance to reconstruct scenes from uncontrolled images, achieving high-quality results and a 1000 ร— rendering speed increase.
ECCV 2024
sym

Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images

Chuanrui Zhang*, Yonggen Ling*โ€ , Minglei Lu, Minghan Qin, Haoqian Wangโ€ 

Website Datasets Code(Coming soon)

  • We present CODERS, a one-stage approach for Category-level Object Detection, pose Estimation and Reconstruction from Stereo images.
AAAI 2024
sym

High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field

Minghan Qin*, Yifan Liu*, Yuelang Xu, Xiaochen Zhao, Yebin Liuโ€ , Haoqian Wangโ€ 

WEBSITE

  • We introduce a novel Spatially-Varying Expression (SVE) conditioning, encompassing both spatial positional features and global expression information.

๐ŸŽ– Honors and Awards

๐Ÿ’ป Research Experience

  • 2023.09 - 2024.4, Harvard University - VCG Lab - Computer Vision Group. I spent a good time with Prof. Hanspeter Pfister.