IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera

Jian Huang^1,2    Chengrui Dong^1,2    Xuanhua Chen^2,3    Peidong Liu^2*

^* denotes corresponding author.

¹Zhejiang University    ²Westlake University    ³Northeastern University   

---

If you like our project, please give us a star ⭐ on GitHub.

This repository is an official PyTorch implementation of the paper "IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera". We explore the possibility of recovering the 3D Gaussian and camera motion trajectory from a single event camera.

📢 News

2025.03.03 🔥Our paper is accepted by CVPR 2025!

2024.10.11 Our paper is available on arXiv.

📋 Overview

IncEventGS processes incoming event stream by dividing it into chunks and representing the camera trajectory as a continuous model. It randomly samples two close consecutive timestamps to integrate the corresponding event streams. Two brightness images are rendered from 3D Gaussian distributions at the corresponding poses, and we minimize the log difference between the rendered images and the accumulated event images. During initialization, a pre-trained depth estimation model estimates depth from the rendered images to bootstrap the system.

📋 Qualitative evaluation of novel view image synthesis on synthetic dataset.

📋 Qualitative evaluation of novel view image synthesis on real dataset.

📋 Representative trajectory comparison