AI Paper Atlas

Research map / 3D vision / Face and shape

COSMU: Complete 3D human shape from monocular unconstrained images

Marco Pesavento, Marco Volino, Adrian Hilton

ECCV 2024 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 1 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
select references with the full energy (orientation, visibility, pose similarity) instead of random (ablation)COSMU · THuman3.0Chamfer distance: 1.485 -> 1.304Improved
add body part-based registration of references (ablation)COSMU · THuman3.0Chamfer distance: 3.546 -> 1.304Improved
use rigid per-part registration instead of non-rigid full-body registration (ablation)COSMU · THuman3.0Chamfer distance: 6.932 -> 1.304Improved
select N_p references per body part instead of a single reference (ablation)COSMU · THuman3.0Chamfer distance: 1.314 -> 1.304Improved
feed both RGB and segmentation masks to part classifier (ablation)COSMU body part classifier · THuman3.0Chamfer distance: 2.249 -> 1.304Improved
use 4 views (3 references) instead of 2 viewsCOSMU · THuman3.0Chamfer distance: 1.355 -> 1.304Improved
leverage real reference views instead of estimating unseen views from the targetCOSMU-2 · THuman3.0Chamfer distance: COSMU-2 1.355 vs ECON 1.368 CD; P2S 1.373 vs 1.365Mixed

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