cs.CVNov 10, 2026

FastWild-GS: Minutes-Scale In-the-Wild Gaussian Splatting via Compact Per-Image Appearance Adaptation

Authors: Donghun Ryu, Seokhyun Kim, Minhyeok Lee

Organizations: Chung-Ang University

Abstract

Internet photos of a scene differ in exposure, illumination and transient objects such as passers-by, so one set of Gaussian colours cannot explain all photos (the in-the-wild setting). Recent in-the-wild Gaussian Splatting methods mostly report hours of per-scene optimization. We present FastWild-GS, which describes each photo by a 128-dimensional Photo Appearance Token and a per-channel transform, a scale and an offset applied to the rendered image (six parameters); a small MLP predicts the colour of each Gaussian from this token and a per-Gaussian feature, replacing the spherical-harmonics colour. The same transform is applied to the renders that score Gaussians for densification and pruning, so appearance differences between photos are not counted as reconstruction error. On PhotoTourism, FastWild-GS trains in 8.8 minutes per scene with the lowest LPIPS among the compared methods, 23x faster than AsymGS, the next best in LPIPS. On NeRF-OSR, it has the best average PSNR, SSIM and LPIPS among the compared methods in 9.7 minutes per scene.

Figures & tables

Explore similar work

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

    Apr 23, 2026Yuki Fujimura, Takahiro Kushida, Kazuya Kitano +23D Gaussian Splatting3D Reconstruction

  2. WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

    Jul 6, 2026Xiyu Zhang, Jingyu Zhuang, Hongjia Zhai +43D Gaussian Splatting3D Reconstruction