AI Paper Atlas

Research map / 3D vision / Human pose estimation

Deep Active Contours for Real-time 6-DoF Object Tracking

Long Wang, Shen Yan, Jianan Zhen, Yu Liu, Maojun Zhang, Guofeng Zhang, Xiaowei Zhou

ICCV 2023 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 25 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
replace handcrafted region statistics with learned boundary prediction (DeepAC vs best optimization-based)DeepAC · RBOT noisy scenes5cm-5deg success rate: 83.2 -> 88.0Improved
DeepAC on easy RBOT scenes where baselines saturateDeepAC · RBOT regular/dynamic light/occlusion5cm-5deg success rate: 95.2 -> 95.6 (regular)No clear effect
DeepAC versus optimization baselines under strict ADD on BCOTDeepAC · BCOTADD-0.02d: 15.3 -> 24.4Improved
add statistical foreground and boundary maps as network inputs (ablation)DeepAC · RBOT5cm-5deg: 90.9 -> 93.3Improved
add multi-level features (ablation)DeepAC · RBOT5cm-5deg: 83.3 -> 93.3Improved
add learned correspondence line uncertainty (ablation)DeepAC · BCOT5cm-5deg: 92.4 -> 94.0Improved
add multi-level features (ablation)DeepAC · BCOT2cm-2deg: 51.7 -> 65.5Improved
increase correspondence lines from 50 to 200 (ablation)DeepAC · RBOT5cm-5deg: 85.8 -> 93.3Improved
increase correspondence lines from 200 to 300 (ablation)DeepAC · RBOT5cm-5deg: 93.3 -> 93.3No clear effect
increase line sample range m from 5 to 9 (ablation)DeepAC · RBOT5cm-5deg: 84.1 -> 93.3Improved
increase line sample range m from 9 to 11 (ablation)DeepAC · BCOT5cm-5deg: 94.0 -> 94.2No clear effect
DeepAC trained on YCB-V versus render-and-compare learned methodsDeepAC- · RBOT (YCB-V trained)ADD-0.02d: 10.9 -> 39.1Improved

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