AI Paper Atlas

Research map / 3D vision / Human pose estimation

Polarimetric Pose Prediction

Daoyi Gao, Yitong Li, Patrick Ruhkamp, Iuliia Skobleva, Magdalena Wysocki, HyunJun Jung, Pengyuan Wang, Arturo Guridi, Benjamin Busam

ECCV 2022 · 3D vision › Human pose estimation · approach: Instance-level 6D object pose · 31 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 polarised RGB input instead of unpolarised RGB (ablation)PPP-Net · ForkADD: 85.4 -> 86.1Improved
use polarised RGB input instead of unpolarised RGB (ablation)PPP-Net · CupADD: 91.1 -> 91.3No clear effect
add normals output head (ablation)PPP-Net · ForkADD: 86.1 -> 92.9Improved
add physical normals as separate input (ablation)PPP-Net · ForkADD: 92.9 -> 95.9Improved
add physical normals as separate input (ablation)PPP-Net · CupADD: 91.3 -> 97.2Improved
add physical normals input (normals error) (ablation)PPP-Net · Forknormal mean error: 11.0 -> 6.5Improved
add NOCS output before Patch-PnP (ablation)PPP-Net · ForkADD: 79.3 -> 95.9Improved
add NOCS output before Patch-PnP (ablation)PPP-Net · TeapotADD: 72.7 -> 99.9Improved
encode physical normals with a dedicated encoder instead of concatenation (ablation)PPP-Net · ForkADD: 87.6 -> 95.9Improved
encode physical normals with a dedicated encoder instead of concatenation (ablation)PPP-Net · KnifeADD: 86.1 -> 96.4Improved
predicted instead of GT bounding box at test (ablation)PPP-Net · CupADD: 99.0 -> 97.2Hurt
use incorrect refractive index (1.5) in training and testing (ablation)PPP-Net · KnifeADD: 96.4 -> 90.1Hurt

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