AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion

Fadi Khatib, Meirav Galun, Ronen Basri

ECCV 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use 3 GNN layers instead of 2 (ablation)VGPA · MegaDepth validation, before final BApose AUC@30: 0.346 -> 0.389Improved
use edge-conditioned message passing instead of GATv2 attention (ablation)VGPA · MegaDepth validation, before final BApose AUC@30: 0.364 -> 0.389Improved
add test-time fine-tuning to pretrained model (ablation)VGPA · MegaDepth validation, before final BApose AUC@30: 0.358 -> 0.389Improved
add pretraining before fine-tuning (ablation)VGPA · MegaDepth validation, before final BApose AUC@30: 0.352 -> 0.389Improved
train the network rather than random init (ablation)VGPA · MegaDepth validation, before final BApose AUC@30: 0.012 -> 0.358Improved
add view re-integration post-processing (ablation)VGPA · MegaDepth (mean)registered images: 327 -> 348 (rot 0.95 -> 1.36)Mixed
replace exhaustive graph with sparse MegaLoc top-30 retrieval graph (ablation)VGPA · 1DSfMrotation error: Piazza del Popolo 5.37 -> 0.57; Yorkminster 0.43 -> 6.32Mixed
estimate intrinsics jointly in BA instead of known intrinsics (ablation)VGPA · MegaDepth scene 0048rotation error: 0.10 -> 0.38Hurt
estimate intrinsics jointly in BA instead of known intrinsics (ablation)VGPA · BlendedMVS scene0rotation error: 0.149 -> 0.122No clear effect
use VGPA instead of RESfM deep factorizationpose estimation · MegaDepth (mean)AUC@30: 0.910 -> 0.927Improved
use VGPA instead of GLOMAPpose estimation · 1DSfM runtime (mean)total time (min): 18.2 -> 2.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy