AI Paper Atlas

Research map / 3D vision / Depth and stereo

Sparse-View Localization via Online Neural 3D Regression

Ludvig Dillén, Magnus Oskarsson, Viktor Larsson

CVPR 2026 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 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
ON3R vs transitive matching, K=2sparse-view localization · MegaDepth K=2recall (5deg,1m): 41.3 -> 71.0Improved
ON3R vs transitive matching on Cambridge, K=4sparse-view localization · Cambridge Landmarks K=4recall (5deg,1m): 91.7 -> 90.0No clear effect
add bundle adjustment after P3P-RANSAC (ablation)ON3R · MegaDepth K=2median translation error (m): 9.31 -> 0.45Improved
add monocular depth prior (MoGe-2) (ablation)ON3R · MegaDepth K=2recall (5deg,1m): 54.3 -> 71.0Improved
reduce max epochs from 500 to 50 (ablation)ON3R · MegaDepth K=2recall (5deg,1m): 71.0 -> 66.0No clear effect
use DISK descriptor instead of SuperPoint (ablation)ON3R · MegaDepth K=2median translation error (m): 0.45 -> 0.41Improved
ON3R vs HLOC on 99% sparsified Aachenstructure-based localization · Aachen Day-Night v1.1 sparsifiedrecall (10deg,5m) Day: 12.5 -> 22.7Improved
ON3R vs HLOC on full Aachen database (K=50)structure-based localization · Aachen Day-Night v1.1 fullrecall (10deg,5m) Day: 99.3 -> 95.1Hurt
ON3R vs HLOC on subsampled Cambridge (K=5, 10)structure-based localization · Cambridge Landmarks subsampledmedian errors and recallMixed
ON3R vs ACE (scene coordinate regression) with few imagessparse-view localization · MegaDepth K=2recall (5deg,1m): 1.3 -> 71.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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