AI Paper Atlas

Research map / 3D vision / Face and shape

Procrustean Regression Networks: Learning 3D Structure of Non-Rigid Objects from 2D Annotations

Sungheon Park, Minsik Lee, Nojun Kwak

ECCV 2020 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 17 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 Procrustean low-rank regularization term (ablation)PRN-FCN · Human3.6M 2D-input (GT-ortho)MPJPE: 144.8 -> 66.7Improved
add the Procrustean low-rank regularization term (ablation)PRN-CNN · Human3.6M RGB inputMPJPE: 164.5 -> 108.9Improved
add the Procrustean low-rank regularization term (ablation)PRN-FCN · 300-VW 2D-inputnormalized error: 0.5201 -> 0.1512Improved
add the Procrustean low-rank regularization term (ablation)PRN-FCN · SURREAL 2D-inputnormalized error: 0.3565 -> 0.1377Improved
weight reprojection error by keypoint detection scoresPRN-FCN · Human3.6M 2D-input (SH fine-tuned)MPJPE: 99.1 -> 95.9Improved
weight reprojection error by keypoint scoresPRN-FCN · Human3.6M Sitting (SH FT)MPJPE: 114.0 -> 102.1Improved
weight reprojection error by keypoint scoresPRN-FCN · Human3.6M SittingDown (SH FT)MPJPE: 141.2 -> 113.2Improved
fine-tune the 2D keypoint detector on Human3.6MPRN-FCN · Human3.6M 2D-input (SH)MPJPE: 124.5 -> 99.1Improved
use PRN instead of C3DPO under perspective projectionPRN-FCN · Human3.6M 2D-input (GT-persp)MPJPE: 95.6 -> 86.4Improved
use PRN instead of C3DPO under orthographic projectionPRN-FCN · Human3.6M 2D-input (GT-ortho)MPJPE: 67.8 -> 66.7No clear effect
train on PRN loss instead of NRSfM-reconstructed labels (SPM)PRN-FCN · Human3.6M 2D-input (GT-ortho)MPJPE: 82.3 -> 66.7Improved
increase ratio of missing input points from 0% to 20% (ablation)PRN-FCN · Human3.6M 2D-inputMPJPE: 66.7 -> 73.8Hurt

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