AI Paper Atlas

Research map / 3D vision / Human pose estimation

"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization"

Muhammad Zubair Irshad, Sergey Zakharov, Rareș Ambruș, Thomas Kollar, Zsolt Kira, Adrien Gaidon

ECCV 2022 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 72 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 ShAPO instead of CenterSnap-RShAPO · REAL2755deg 10cm mAP: 31.6 -> 57.0Improved
use ShAPO instead of CenterSnap-RShAPO · REAL27510deg 10cm mAP: 70.9 -> 78.0Improved
use ShAPO instead of CenterSnap-RShAPO · CAMERA255deg 10cm mAP: 71.7 -> 75.9Improved
use ShAPO instead of CenterSnap-RShAPO · REAL275IOU50 mAP: 80.2 -> 79.0Hurt
use ShAPO shape optimization instead of baseline reconstructionShAPO · NOCS reconstructionmean chamfer distance (CAMERA25): 0.20 -> 0.14Improved
use ShAPO shape optimization instead of baseline reconstructionShAPO · NOCS reconstructionmean chamfer distance (REAL275): 0.32 -> 0.15Improved
add differentiable optimization of texture latent (ablation)ShAPO · NOCS REAL275texture PSNR: 11.41 -> 20.64Improved
add fine-tuning of texture network weights after optimization (ablation)ShAPO · NOCS REAL275texture PSNR: 20.64 -> 24.32Improved
use octree sampling LoD6 instead of ordinary grid 60 (ablation)ShAPO · NOCS reconstructiontime (s): 30.51 -> 6.88Improved
use octree sampling LoD6 instead of ordinary grid 60 (ablation)ShAPO · NOCS reconstructionGPU memory (MB): 7850 -> 2880Improved
use octree sampling LoD6 instead of ordinary grid 60 (ablation)ShAPO · NOCS reconstructiontexture PSNR: 19.52 -> 13.63Hurt
raise octree level from LoD6 to LoD7 (ablation)ShAPO · NOCS reconstructiontexture PSNR: 13.63 -> 16.14Improved

Later papers that compared with this method

1 later accepted paper reports ShAPO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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