AI Paper Atlas

Research map / 3D vision / Human pose estimation

Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

Yuan Liu, Yilin Wen, Sida Peng, Cheng Lin, Xiaoxiao Long, Taku Komura, Wenping Wang

ECCV 2022 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 168 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 the volume-based pose refiner (ablation)Gen6D · GenMOPADD-0.1d: 17.90 -> 50.39Improved
add the volume-based pose refiner (ablation)Gen6D · GenMOPPrj-5: 36.73 -> 82.64Improved
add global normalization and reference view transformer to the selector (ablation)Viewpoint selector · GenMOPADD-0.1d: 14.88 -> 17.90Improved
add global normalization and reference view transformer to the selector (ablation)Viewpoint selector · GenMOPPrj-5: 30.28 -> 36.73Improved
replace DeepIM refiner with volume refiner (ablation)Gen6D · GenMOPPrj-5: 42.16 -> 77.54Improved
replace pretrained DeepIM with volume refiner (ablation)Gen6D · GenMOPADD-0.1d: 19.53 -> 50.39Improved
add real-data (LINEMOD) training to synthetic+GenMOP training (ablation)Gen6D · GenMOPADD-0.1d: 39.94 -> 50.39Improved
add GenMOP real data to synthetic training (ablation)Gen6D · GenMOPADD-0.1d: 33.70 -> 39.94Improved
use 3 refinement iterations instead of 2 (ablation)Gen6D · GenMOPADD-0.1d: 53.32 -> 50.39No clear effect
use 1 refinement iteration instead of none (ablation)Gen6D · GenMOPADD-0.1d: 17.90 -> 38.59Improved
reduce reference images from all to 8 (ablation)Gen6D · GenMOPPrj-5: 82.64 -> 37.33Hurt
reduce reference images from all to 64 (ablation)Gen6D · GenMOPPrj-5: 82.64 -> 82.30No clear effect

Later papers that compared with this method

3 later accepted papers report Gen6D as a baseline in their results tables; 3 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