Click-Gaussian: Interactive Segmentation to Any 3D Gaussians

TL;DR

Click-Gaussian introduces a fast, accurate interactive segmentation method for 3D Gaussians that avoids post-processing and handles noisy, conflicting 2D segmentation cues effectively, enabling real-time scene manipulation.

Contribution

The paper presents Click-Gaussian, a novel approach that learns distinguishable feature fields at two levels and employs Global Feature-guided Learning to improve 3D segmentation accuracy and speed.

Findings

Runs in 10 ms per click, 15-130x faster than previous methods.

Significantly improves segmentation accuracy.

Effectively handles noisy and conflicting 2D segmentation cues.

Abstract

Interactive segmentation of 3D Gaussians opens a great opportunity for real-time manipulation of 3D scenes thanks to the real-time rendering capability of 3D Gaussian Splatting. However, the current methods suffer from time-consuming post-processing to deal with noisy segmentation output. Also, they struggle to provide detailed segmentation, which is important for fine-grained manipulation of 3D scenes. In this study, we propose Click-Gaussian, which learns distinguishable feature fields of two-level granularity, facilitating segmentation without time-consuming post-processing. We delve into challenges stemming from inconsistently learned feature fields resulting from 2D segmentation obtained independently from a 3D scene. 3D segmentation accuracy deteriorates when 2D segmentation results across the views, primary cues for 3D segmentation, are in conflict. To overcome these issues, we propose Global Feature-guided Learning (GFL). GFL constructs the clusters of global feature candidates from noisy 2D segments across the views, which smooths out noises when training the features of 3D Gaussians. Our method runs in 10 ms per click, 15 to 130 times as fast as the previous methods, while also significantly improving segmentation accuracy. Our project page is available at https://seokhunchoi.github.io/Click-Gaussian