SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians
Authors:
Preprint
Abstract
Implicit neural representation methods have shown impressive advancements in learning 3D scenes from unstructured in-the-wild photo collections but are still limited by the large computational cost of volumetric rendering. More recently, 3D Gaussian Splatting emerged as a much faster alternative with superior rendering quality and training efficiency, especially for small-scale and object-centric scenarios. Nevertheless, this technique suffers from poor performance on unstructured in-the-wild data. To tackle this, we extend over 3D Gaussian Splatting to handle unstructured image collections. We achieve this by modeling appearance to seize photometric variations in the rendered images. Additionally, we introduce a new mechanism to train transient Gaussians to handle the presence of scene occluders in an unsupervised manner. Experiments on diverse photo collection scenes and multi-pass acquisition of outdoor landmarks show the effectiveness of our method over prior works achieving state-of-the-art results with improved efficiency.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Mip-Splatting: Alias-Free 3D Gaussian Splatting2024
- VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction2024
- K-Planes: Explicit Radiance Fields in Space, Time, and Appearance2023
- NeRF for Outdoor Scene Relighting2022
- Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly- Throughs2022
- Hallucinated Neural Radiance Fields in the Wild2022
- NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections2021
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Image Matching Across Wide Baselines: From Paper to PracticeInternational Journal of Computer Vision, 2020
- Point Sample Rendering1998