ReCoGS: Real-time ReColoring for Gaussian Splatting scenes

TL;DR

ReCoGS introduces a real-time, user-friendly recoloring pipeline for Gaussian Splatting scenes, enabling precise editing and interactive experimentation, advancing scene editing capabilities in 3D reconstructions.

Contribution

The paper presents a novel real-time recoloring method for Gaussian Splatting scenes, allowing precise user control and interactive editing, which was not previously available.

Findings

Enables real-time recoloring of 3D scenes

Provides a user-friendly interface for scene editing

Demonstrates interactive editing with Gaussian Splatting

Abstract

Gaussian Splatting has emerged as a leading method for novel view synthesis, offering superior training efficiency and real-time inference compared to NeRF approaches, while still delivering high-quality reconstructions. Beyond view synthesis, this 3D representation has also been explored for editing tasks. Many existing methods leverage 2D diffusion models to generate multi-view datasets for training, but they often suffer from limitations such as view inconsistencies, lack of fine-grained control, and high computational demand. In this work, we focus specifically on the editing task of recoloring. We introduce a user-friendly pipeline that enables precise selection and recoloring of regions within a pre-trained Gaussian Splatting scene. To demonstrate the real-time performance of our method, we also present an interactive tool that allows users to experiment with the pipeline in practice. Code is available at https://github.com/loryruta/recogs.