Pith. sign in

REVIEW 2 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2508.17972 v1 pith:4HFZLTKL submitted 2025-08-25 cs.CV

classification cs.CV
keywords sceneimagesregressioninputlargesail-reconaugmentingcamera
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 then 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. We will publish our model and code. Code and models are publicly available at: https://hkust-sail.github.io/ sail-recon/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MAGiSt3R is a multi-agent feed-forward 3D reconstruction system using a learned submap-merging model (MAGMA) and pose graph optimization to align local maps from multiple monocular RGB cameras into one consistent map ...

  2. Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    Argus plus Realsee3D deliver state-of-the-art metric camera pose, depth, and point-cloud reconstruction from unordered indoor panoramas via learned covisibility anchoring and geometric factorization.

Pith tools