AI Paper Atlas

Research map / 3D vision / Depth and stereo

DeepTAM: Deep Tracking and Mapping

Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox

ECCV 2018 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 226 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 learned optical flow features to tracking network (ablation)DeepTAM tracking · RGB-D benchmark averagetranslational RMSE (m/s): 0.050 -> 0.043Improved
predict multiple pose hypotheses instead of a single pose (ablation)DeepTAM tracking · RGB-D benchmark averagetranslational RMSE (m/s): 0.043 -> 0.040Improved
learned tracking versus classic RGB-D SLAM keyframe odometryDeepTAM tracking · RGB-D benchmark averagetranslational RMSE (m/s): 0.060 -> 0.040Improved
combined DeepTAM tracking and mapping versus CNN-SLAMDeepTAM · RGB-D benchmark averagetranslational RMSE (m/s): 0.253 -> 0.086Improved
use 6 frames instead of 2 in the fixed band cost volume (ablation)DeepTAM mapping · MVS testsc-inv: 0.193 -> 0.160Improved
use 10 frames instead of 6 in the fixed band cost volume (ablation)DeepTAM mapping · MVS testsc-inv: 0.160 -> 0.159No clear effect
add narrow band refinement, 3 iterations (ablation)DeepTAM mapping · MVS testsc-inv: 0.156 -> 0.132Improved
increase narrow band iterations from 3 to 5 (ablation)DeepTAM mapping · MVS testsc-inv: 0.132 -> 0.130No clear effect
increase narrow band iterations from 3 to 5 (ablation)DeepTAM mapping · SUN3D testsc-inv: 0.125 -> 0.128Hurt
DeepTAM mapping versus DTAM on weakly textured indoor dataDeepTAM mapping · SUNCG testsc-inv: 0.343 -> 0.128Improved
use 64 labels instead of 32 for SGM and DTAM cost volume (ablation)SGM, DTAM baselines · mapping comparisondepth errorImproved
add noise to camera posesSGM, DTAM vs DeepTAM · mapping with noisy posesdepth qualityMixed

Later papers that compared with this method

3 later accepted papers report DeepTAM as a baseline in their results tables; 2 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 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