VIRGi: View-dependent Instant Recoloring of 3D Gaussians Splats

TL;DR

VIRGi introduces a fast, view-dependent scene recoloring method for 3D Gaussian Splatting that enables real-time editing by separating diffuse and specular components and using multi-view training.

Contribution

The paper presents a novel architecture and training strategy for rapid, view-dependent recoloring of 3D scenes modeled by Gaussian Splatting, with minimal user input.

Findings

Enables scene recoloring in just two seconds.

Preserves view-dependent effects like specular highlights.

Outperforms Neural Radiance Field-based methods in quality.

Abstract

3D Gaussian Splatting (3DGS) has recently transformed the fields of novel view synthesis and 3D reconstruction due to its ability to accurately model complex 3D scenes and its unprecedented rendering performance. However, a significant challenge persists: the absence of an efficient and photorealistic method for editing the appearance of the scene's content. In this paper we introduce VIRGi, a novel approach for rapidly editing the color of scenes modeled by 3DGS while preserving view-dependent effects such as specular highlights. Key to our method are a novel architecture that separates color into diffuse and view-dependent components, and a multi-view training strategy that integrates image patches from multiple viewpoints. Improving over the conventional single-view batch training, our 3DGS representation provides more accurate reconstruction and serves as a solid representation for the recoloring task. For 3DGS recoloring, we then introduce a rapid scheme requiring only one manually edited image of the scene from the end-user. By fine-tuning the weights of a single MLP, alongside a module for single-shot segmentation of the editable area, the color edits are seamlessly propagated to the entire scene in just two seconds, facilitating real-time interaction and providing control over the strength of the view-dependent effects. An exhaustive validation on diverse datasets demonstrates significant quantitative and qualitative advancements over competitors based on Neural Radiance Fields representations.