AI Paper Atlas

Research map / 3D vision / Face and shape

Single View Metrology in the Wild

Rui Zhu, Xingyi Yang, Yannick Hold-Geoffroy, Federico Perazzi, Jonathan Eisenmann, Kalyan Sunkavalli, Manmohan Chandraker

ECCV 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 40 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 two cascade refinement layers (SN-L1 to SN-L3) (ablation)SN-L1 · COCO-Scale-person testLvt reprojection error (mean): 0.1502 -> 0.0717Improved
add two cascade refinement layers (SN-L1 to SN-L3) (ablation)SN-L1 · KITTI-personLvt reprojection error (mean): 0.0980 -> 0.0331Improved
train with multiple categories (people and cars) (ablation)SN-L3 · COCO-Scale-person testLvt reprojection error (mean): 0.0717 -> 0.0613Improved
train with multiple categories (people and cars) (ablation)SN-L3 · KITTI-personLvt reprojection error (mean): 0.0331 -> 0.0283Improved
train with multiple categories (people and cars) (ablation)SN-L3 · KITTI-personEhobj object height error (mean): 0.0956 -> 0.0849Improved
predict keypoints and upright height with upright ratio (ablation)SN-L3 · COCO-Scale-person testLvt reprojection error (mean): 0.0717 -> 0.0540Improved
predict keypoints and upright height with upright ratio (ablation)SN-L3 · COCO-Scale-person A/B realismuser preference: 42.8% -> 57.2%Improved
predict keypoints and upright height with upright ratio (ablation)SN-L3 · IMDB-23K (non-standing persons)Ehobj upright height error (mean): 0.1591 -> 0.1212Improved
predict keypoints and upright height with upright ratio (ablation)SN-L3 · IMDB-23KEhobj upright height error (mean): 0.0891 -> 0.1003Hurt
predict keypoints and upright height with upright ratio (ablation)SN-L3 · KITTI-personEhobj object height error (mean): 0.0956 -> 0.1014Hurt
replace PGM baseline with learned SN-L3-kps-canPGM · COCO-Scale-person A/B realismuser preference: 40.5% -> 59.5%Improved
learn object heights instead of PGMPGM · IMDB-23KEhobj upright height error (mean): 0.2234 -> 0.0891Mixed

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