Rui Li

I am a Ph.D. student specializing in 3D computer vision, with a focus on 3D reconstruction and spatial reasoning. Previously, I was a Student Research Scientist at Meta Reality Labs in Zurich.

I was a student researcher at King Abdullah University of Science and Technology, supervised by Prof. Peter Wonka. Prior to that, I was a visiting Ph.D. student at the Computer Vision Laboratory (CVL), ETH Zürich, where I worked with Dr. Federico Tombari and Prof. Luc Van Gool. I was also mentored by Dr. Dong Gong and Dr. Wei Yin on 3D reconstruction projects.

Email  /  Scholar  /  Github  /  Twitter(X)

photo
News
  • [2025.04.28] We present LaRI, a single-view unseen scene reasoning model. Checkout our 🚀Demo🚀!
  • [2025.03.23] Sparse2DGS is accepted to CVPR 2025!
  • [2024.09.30] We won the first place of the TRICKY Depth Challenge at ECCV 2024!
  • [2024.04.01] KYN (VL-guided single-view 3D reconstruction) is accepted to CVPR 2024!
  • [2024.03.30] GoMVS ( ranks 1st on Tank & Temples Advanced set) is accepted to CVPR 2024!
  • [2023.04.18] The code and paper of the DyMultiDepth (CVPR 2023) has been released!
Research
Image LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning
Rui Li, Biao Zhang, Zhenyu Li, Federico Tombari, Peter Wonka
arXiv Preprint, 2025.
project page / arXiv / code / huggingface

A single-view geometric reasoning method that models unseen 3D surfaces using layered point maps, unifying object- and scene-level tasks.

Image Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views
Jiang Wu, Rui Li, Yu Zhu, Rong Guo, Jinqiu Sun, Yanning Zhang
Computer Vision and Pattern Recognition (CVPR), 2025
arXiv (Coming soon) / code

A 3D reconstruction method that produces a watertight mesh from as few as three input images within minutes.

Image Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
Rui Li, Tobias Fischer, Mattia Segu, Marc Pollefeys, Luc Van Gool, Federico Tombari
Computer Vision and Pattern Recognition (CVPR), 2024
project page / arXiv / code

A single-view 3D reconstruction method that disambiguates occluded scene geometry by utilizing Vision-Language semantics and spatial reasoning.

Image GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Jiang Wu*, Rui Li*, Haofei Xu, Wenxun Zhao, Yu Zhu, Jinqiu Sun, Yanning Zhang (* equal contribution)
Computer Vision and Pattern Recognition (CVPR), 2024
project page / arXiv / code

A multi-view stereo approach with geometrically consistent matching cost aggregation using monocular normals.
1st place on Tanks and Temples (Advanced) leaderboard.

Image Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
Rui Li, Dong Gong, Wei Yin, Hao Chen, Yu Zhu, Kaixuan Wang, Xiaozhi Chen, Jinqiu Sun, Yanning Zhang
Computer Vision and Pattern Recognition (CVPR), 2023
project page / video / arXiv / code

A multi-frame depth estimation approach that handles the dynamic areas by fusing monocular and multi-view cues in a mask-free manner.

Image Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance
Rui Li, Danna Xue, Shaolin Su, Xiantuo He, Qing Mao, Yu Zhu, Jinqiu Sun, Yanning Zhang
Pattern Recognition (PR), 2023
paper / code (coming soon)

A semantic-guided self-supervised depth estimation method that conducts implicit/explicit semantic guidance for high-quality and sharp depth.

Image Enhancing Self-supervised Monocular Depth Estimation via Incorporating Robust Constraints
Rui Li, Xiantuo He, Yu Zhu, Xianjun Li, Jinqiu Sun, Yanning Zhang
ACM International Conference on Multimedia (ACM MM), 2020

A self-supervised depth estimation method that incorporates robust constraints to improve photometric supervision.

Academic Services
  • Conference Reviewer
    • CVPR: 2023, 2024
    • ECCV: 2022, 2024
    • ICCV: 2023, 2025
    • 3DV: 2023, 2025

awesome website template