AI Paper Atlas

Research map / 3D vision / Depth and stereo

CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval

Feiran Wang, Junyi Wu, Dawen Cai, Yuan Hong, Yan Yan

ICLR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 3 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 3D features to 2D matching (ablation)CogniMap3D memory recall · DAVIS scene matchingaccuracy (%): 93.5 -> 96.8Improved
add ICP geometric validation (ablation)CogniMap3D memory recall · DAVIS scene matchingaccuracy (%): 96.8 -> 97.5Improved
add ICP validation and 3D features (ablation)CogniMap3D memory recall · DAVIS scene matchingthroughput (q/s): 18.2 -> 6.8Hurt
add memory update (ablation)CogniMap3D · 7-Scenes reconstructionAcc mean: 0.086 -> 0.082Improved
add memory update (ablation)CogniMap3D · 7-Scenes reconstructionNC mean: 0.751 -> 0.789Improved
add memory (ablation)CogniMap3D · Long-sequence KITTI poseATE: 0.068 -> 0.060Improved
use factor graph refinement instead of PnP+RANSAC (ablation)CogniMap3D · Camera pose analysis (TUM-dynamic)ATE: 0.025 -> 0.012Improved
use factor graph refinement instead of DPVO (ablation)CogniMap3D · Camera pose analysis (TUM-dynamic)ATE: 0.019 -> 0.012Improved
add factor graph optimization (ablation)CogniMap3D · Camera pose analysis (TUM-dynamic)RPE rot: 0.510 -> 0.311Improved
add severe noise to initial posesCogniMap3D · TUM-dynamicATE: 0.012 -> 0.019Hurt
increase memory size from 50 to 200CogniMap3D · DAVIS scene matchingaccuracy (%): 96 -> 97.5No clear effect
use CogniMap3D memory instead of VGGTCogniMap3D · KITTI reconstructionAcc mean: 0.071 -> 0.052Improved

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