AI Paper Atlas

Research map / 3D vision / Face and shape

Monocular Real-Time Volumetric Performance Capture

Ruilong Li, Yuliang Xiu, Shunsuke Saito, Zeng Huang, Kyle Olsewski, Hao Li

ECCV 2020 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 93 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 point-ohem sampling (ablation)PIFu-based real-time model · RenderPeopleChamfer distance: 1.561 -> 1.397Improved
add point-ohem sampling (ablation)PIFu-based real-time model · BUFFP2S distance (top-10 worst): 9.556 -> 7.092Improved
add item-ohem on top of point-ohem (ablation)Ours+P · top-10 worst cases, BUFFChamfer* and P2S*: 7.092 -> 5.874Improved
add item-ohem on top of point-ohem (ablation)Ours+P · RenderPeopleChamfer distance (average): 1.397 -> 1.431Hurt
replace stacked hourglass with HRNet encoder (ablation)HG-MLP · RenderPeopleChamfer distance: 1.684 -> 1.602Improved
replace stacked hourglass with HRNet encoder (ablation)HG-MLP · Runtimefps: 12 -> 14Improved
add conditional batch norm (CBN) (ablation)HRNet-MLP · RenderPeopleChamfer distance: 1.602 -> 1.584Improved
add SoftZ depth representation (ablation)HRNet-CBN · RenderPeopleChamfer distance: 1.584 -> 1.561Improved
add SoftZ depth representation (ablation)HRNet-CBN · BUFFP2S distance: 3.585 -> 3.613Hurt
use hierarchical surface localization instead of brute force (ablation)PIFu inference · reconstruction timeseconds per frame: 30 seconds to 0.14 secondsImproved
add direct mesh-free rendering (ablation)hierarchical localization · novel-view renderingseconds per frame: 0.14 seconds to 0.06 secondsImproved
add binarized octree localization instead of proposed method (ablation)brute-force baseline · reconstructioncompletenessHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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