Weining Ren | 任伟宁

I am a PhD student at HKU CDS, advised by Dr. Kai Han. My previous research primarily focuses on 3D Vision.

I obtained my Master degree from ETH Zürich working with Prof. Marc Pollefeys and Dr. Songyou Peng. Prior to that, I obtained a bachelor degree from THU supervised by Prof. Diange Yang and Dr. Kun Jiang. I'm Lucky to have interned at Huawei Zürich with Dr. Stamatios Georgoulis and Baidu VIS with Dr. Xiao Tan.

Email  /  Google Scholar  /  Github

profile photo

Research

My previous research primarily focuses on 3D vision, including SLAM, NeRF, depth estimation and optical flow. Currently, I am working on feed-forward 3D reconstruction models, and I have a growing interest in generative models and sparse attention.
: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
Weining Ren, Hongjun Wang, Xiao Tan, Kai Han
NeurIPS, 2025
paper | project page | code

Fin3R fine-tunes feed-forward 3D reconstruction models to enhance fine details and improve robustness.

NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild
Weining Ren*, Zihan Zhu*, Boyang Sun, Jiaqi Chen, Marc Pollefeys, Songyou Peng
CVPR, 2024
paper | project page | video | code

We enable robust novel view synthesis from casually captured in-the-wild images.

Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
Stamatios Georgoulis*, Weining Ren*, Alfredo Bochicchio, Daniel Eckert, Yuanyou Li, Abel Gawel
3DV, 2024 (Spotlight)

paper | video

We segment moving objects with event camera.

Honors

    NeurIPS Top Reviewer, NeurIPS, 2025

    HKPFS, The University of Hong Kong, 2024-2028

    Degree with Distiction, ETH Zürich, 2024

    National Scholarship, Tsinghua University, 2020

Thanks Jon Barron for the nice template.