WildGaussians: 3D Gaussian Splatting in the Wild

TL;DR

WildGaussians enhances 3D Gaussian Splatting to effectively handle occlusions, dynamic objects, and illumination changes in in-the-wild scenes, achieving state-of-the-art results with real-time rendering.

Contribution

We introduce WildGaussians, a novel method that integrates appearance modeling with 3DGS using robust features to improve in-the-wild scene reconstruction.

Findings

Outperforms 3DGS and NeRF on in-the-wild data

Maintains real-time rendering speeds

Effectively handles occlusions and appearance changes

Abstract

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework.