AI Paper Atlas

Research map / 3D vision / Face and shape

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction

Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll

ECCV 2020 · 3D vision › Face and shape · approach: Full-body avatar reconstruction

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 inner body surface prediction to outer-only registration (ablation)IP-Net registration · Dressed human scans, 50 test (SMPL+D registration, vertex error cm)vertex-to-vertex error (cm), outer: 11.84 -> 11.54Improved
add part correspondences to outer+inner registration (ablation)IP-Net registration · Dressed human scans, 50 test (SMPL+D registration, vertex error cm)vertex-to-vertex error (cm), outer: 11.54 -> 3.67Improved
add part correspondences to outer+inner registration (ablation)IP-Net registration · Dressed human scans, 50 test (SMPL+D registration, vertex error cm)vertex-to-vertex error (cm), inner: 11.14 -> 3.32Improved
register SMPL+D to IP-Net predictions instead of IF-Net reconstructionSMPL+D registration · Dressed human scans, 50 test (SMPL+D registration, vertex error cm)vertex-to-vertex error (cm): 13.88 -> 3.67Improved
register to implicit predictions instead of regressing SMPL+D parametersSMPL+D fitting · Dressed human scans, 50 test (SMPL+D registration, vertex error cm)vertex-to-vertex error (cm): 32.45 -> 3.67Improved
use IP-Net predictions instead of IP-Net correspondences only on single view (ablation)SMPL+D registration · Single-view point cloudvertex-to-vertex error (cm), outer: 14.43 -> 5.11Improved
jointly predict inner and outer surface instead of two independent networks (ablation)IP-Net · Inner/outer surface inter-penetrationintersecting face area (mm^2): 2000.71mm^2 -> 0.65mm^2Improved
use IP-Net part labels for scan registration instead of registering sparse point cloudSMPL+D registration · Scan registrationvertex-to-vertex error (cm), outer: 13.93 -> 3.67Improved
use IP-Net instead of IF-Net for outer surface reconstructionimplicit reconstruction · Outer surface reconstructionvertex-to-surface error (mm): 4.86 -> 4.95No clear effect

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