WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images

TL;DR

WildSplatter is a feed-forward 3D Gaussian Splatting model trained on unconstrained images, enabling real-time 3D reconstruction and appearance control under varying lighting without iterative optimization.

Contribution

It introduces a novel approach that jointly learns 3D Gaussians and appearance embeddings from unconstrained images for fast, pose-free 3D scene reconstruction and appearance modulation.

Findings

Reconstructs 3D Gaussians from sparse views in under one second.

Outperforms existing pose-free 3DGS methods on real-world datasets with varying illumination.

Enables flexible appearance control under diverse lighting conditions.

Abstract

We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality, real-time rendering; however, it typically requires iterative optimization and multi-view images captured under consistent lighting with known camera parameters. WildSplatter is trained on unconstrained photo collections and jointly learns 3D Gaussians and appearance embeddings conditioned on input images. This design enables flexible modulation of Gaussian colors to represent significant variations in lighting and appearance. Our method reconstructs 3D Gaussians from sparse input views in under one second, while also enabling appearance control under diverse lighting conditions. Experimental results demonstrate that our approach outperforms existing pose-free 3DGS methods on challenging real-world datasets with varying illumination.