https://jsxzs.github.io/sa4d/

Segment Any 4D Gaussians
https://jsxzs.github.io/sa4d/

3d-vision 4d-gaussian-splatting 4d-segmentation computer-vision dynamic-scene gaussian-splatting

Last synced: about 1 month ago
JSON representation

Segment Any 4D Gaussians

• Host: GitHub
• URL: https://jsxzs.github.io/sa4d/
• Owner: jsxzs
• License: apache-2.0
• Created: 2024-07-15T01:39:59.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-15T01:50:16.000Z (6 months ago)
• Last Synced: 2024-07-15T02:54:00.561Z (6 months ago)
• Topics: 3d-vision, 4d-gaussian-splatting, 4d-segmentation, computer-vision, dynamic-scene, gaussian-splatting
• Homepage: https://jsxzs.github.io/sa4d
• Size: 1.36 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        
# Segment Any 4D Gaussians

### [Project Page](https://jsxzs.github.io/sa4d/) 

![Teaser image](assets/teaserfig.png)

## Abstract

Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and understanding 3D scenes. Similarly, various 4D representations have demonstrated the ability to capture the dynamics of the 4D world. However, there is a dearth of research focusing on segmentation within 4D representations. In this paper, we propose to Segment Any 4D Gaussians (SA4D), the first framework to segment anything in the 4D digital world based on 4D Gaussians. In SA4D, an efficient temporal identity feature field is introduced to handle Gaussian drifting, with the potential to learn precise identity feature from noisy and sparse input. Additionally, a 4D segmentation refinement process is proposed to remove artifacts. Our SA4D achieves precise, high-quality segmentation within seconds in 4D Gaussians and shows the ability of removal, recoloring, composition and rendering high quality novel anything masks.

## 🦾 Updates

- 7/15/2024: Initialize the project. Code will be available within this month.