AI Paper Atlas

Research map / 3D vision / Depth and stereo

iMAP: Implicit Mapping and Positioning in Real-Time

Edgar Sucar, Shikun Liu, Joseph Ortiz, Andrew J. Davison

ICCV 2021 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 761 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 iMAP implicit MLP map instead of TSDF fusioniMAP · Replica (8 scenes)completion ratio (<5cm %): 75.09 -> 79.06Improved
use iMAP implicit MLP map instead of TSDF fusioniMAP · Replica office-3completion ratio (<5cm %): 65.87 -> 77.34Improved
use iMAP instead of TSDF fusion for accuracyiMAP · Replica (8 scenes)accuracy (cm): 3.45 -> 4.43Hurt
use MLP of width 256 instead of TSDF 256^3 voxel gridiMAP · memorymemory (MB): 67.10 -> 1.04Improved
use iMAP instead of ORB-SLAM2/BAD-SLAM for trackingiMAP · TUM RGB-DATE RMSE (cm): 1.6 -> 4.9Hurt
reduce network width from 256 to 128 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 75.79Hurt
increase network width from 256 to 512 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 76.91No clear effect
reduce keyframe window from 5 to 3 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 75.82Hurt
increase keyframe window from 5 to 10 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 77.35No clear effect
increase pixel samples from 200 to 400 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 77.49No clear effect
reduce pixel samples from 200 to 100 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 77.33No clear effect
raise keyframe selection threshold from 0.65 to 0.85 (ablation)iMAP · Replica office-2completion ratio (<5cm %): 77.22 -> 78.03No clear effect

Later papers that compared with this method

5 later accepted papers report iMAP as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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