SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization

Junyuan Deng, Heng Li, Tao Xie, Weiqiang Ren, Qian Zhang, Ping Tan, Xiaoyang Guo

Keywords: Structure from Motion, Scene Regression, Visual Localizaiton

TL;DR: Solving Large SfM by Augmenting Scene Regression with Localization

Abstract: Scene regression methods, such as VGGT, solve the Structure-from-Motion (SfM) problem by directly regressing camera poses and 3D scene structures from input images. They demonstrate impressive performance in handling images under extreme viewpoint changes. However, these methods struggle to handle a large number of input images. To address this problem, we introduce SAIL-Recon, a feed-forward Transformer for large scale SfM, by augmenting the scene regression network with visual localization capabilities. Specifically, our method first computes a neural scene representation from a subset of anchor images. The regression network is fine-tuned to reconstruct all input images conditioned on this neural scene representation. Comprehensive experiments show that our method not only scales efficiently to large-scale scenes, but also achieves state-of-the-art results on both camera pose estimation and novel view synthesis benchmarks, including TUM-RGBD, CO3Dv2, and Tanks & Temples. Code and models are publicly available at: https://hkust-sail.github.io/sail-recon/.

Submission Number: 53