AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features

Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann

ICLR 2026 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 1 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
add scale normalization of mapping translations (ablation)FastForward · Cambridge Landmarksaccuracy 10cm 10deg (%): 1.8 -> 26.7Improved
add scale normalization of mapping translations (ablation)FastForward · Wayspotsaccuracy 10cm 10deg (%): 47.0 -> 51.4Improved
add scale normalization of mapping translations (ablation)FastForward · Indoor6accuracy 10cm 10deg (%): 83.4 -> 91.5Improved
add scale normalization of mapping translations (ablation)FastForward · RIO10 (val)accuracy 10cm 10deg (%): 35.9 -> 40.6Improved
add scale normalization of mapping translations (ablation)FastForward · 7-Scenesaccuracy 10cm 10deg (%): 89.1 -> 90.2Improved
select mapping images by retrieval instead of random sampling (ablation)FastForward · Wayspotsaccuracy 10cm 10deg (%): 43.9 -> 51.4Improved
select mapping images by retrieval instead of uniform sampling (ablation)FastForward · Wayspotsaccuracy 10cm 10deg (%): 47.8 -> 51.4Improved
remove retrieval stepReloc3r · Wayspotsaccuracy 10cm 10deg (%): 37.1 -> 19.7Hurt
increase number of mapping images in map representation (ablation)FastForward · Map-free valaccuracy (all thresholds)Improved
increase number of mapping features from 150 to 3,000 (ablation)FastForward · Map-free valaccuracy 10cm 10deg / 25cm 5degNo clear effect
increase number of mapping features (ablation)FastForward · Map-free valaccuracy 10cm 1degImproved
use scene-specific network training (ACE) instead of FastForward on Wayspots translationFastForward · Wayspotsmedian translation error (m): 1.33 -> 0.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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