AI Paper Atlas

Research map / 3D vision / Depth and stereo

Unordered Landmark Visual Navigation

Hao Ren, Junzhe Zhu, Yihan Li, Zetong Bi, Le Zheng, Zhi Li, Yiqing Yuan, Zhaoliang Wan, Dizhe Zhang, Lu Qi, HUI CHENG

ECCV 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
add maximum spanning forest refinement (ablation)RAVEL · GRScenes mappingF1: 0.5157 -> 0.7365Improved
add adaptive verification threshold (AVP tau) (ablation)RAVEL w/o MSF · GRScenes mappingF1: 0.4496 -> 0.5157Improved
add geometric verification and MSF on top of top-k retrieval (ablation)Top-k ANN · GRScenes mappingF1: 0.2156 -> 0.7365Improved
raise retrieval top-k from 2 to 5 (ablation)PlaceNav · GRScenes mappingF1: 0.6043 -> 0.3731Hurt
add entropy-adaptive fusion (ablation)BPL · GRScenes localizationAccuracy (%): 90.57 -> 95.49Improved
increase propagation depth k from 1 to 5 (ablation)BPL · GRScenes localizationAccuracy (%): 95.49 -> 92.73Hurt
replace temporal-distance localization with BPL (ablation)ULVN+ViNT · GRScenes navigationSuccess rate (%): 59.6 -> 68.1Improved
add temporal distance loss in local planner training (ablation)ULVN+ViNT · GRScenes navigationSuccess rate (%): 31.0 -> 68.1Improved
add temporal distance loss in local planner training (ablation)ULVN+NoMaD · GRScenes navigationSuccess rate (%): 54.3 -> 71.9Improved
use BPL graph-based belief propagation instead of ViNT temporal distancelocalization · GRScenes difficult pathsAccuracy (%): 70.50 -> 93.99Improved
add image noise perturbationRAVEL · GRScenes mappingF1: 0.7365 -> 0.6882No clear effect
add image noise perturbationViNT top 5 · GRScenes mappingF1: 0.3806 -> 0.3281Hurt

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