Xin Fei

About Research

Xin Fei 费昕

Hi there! I will be joining School of Computing, NUS as a PhD student (starting Aug. 2025), advised by Prof. Lin Shao. My research focuses on Robotics for Vision-Language-Action (VLA) models and Computer Vision.

Currently, I am an undergraduate student at Department of Automation, Tsinghua University. My research interests focus on building neural embodied systems capable of:

Perceiving, reasoning, and planning in real-world environments
Performing a wide range of tasks, such as manipulation and grasping

Research

Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model

Shengjun Zhang, Jinzhao Li, Xin Fei, Hao Liu, Yueqi Duan

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025

Website

arXiv

Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images

Shengjun Zhang, Xin Fei, Fangfu Liu, Haixu Song, Yueqi Duan

Conference on Neural Information Processing Systems (NeurIPS) 2024

Website

arXiv

Code

GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds

Shengjun Zhang, Xin Fei, Yueqi Duan

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024

arXiv

Code

Build on Nicholas's website. Last updated: Apr, 2025.