AI Paper Atlas

Research map / 3D vision / Face and shape

Complete 3D Human Reconstruction From a Single Incomplete Image

Junying Wang, Jae Shin Yoon, Tuanfeng Y. Wang, Krishna Kumar Singh, Ulrich Neumann

CVPR 2023 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 19 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
use generative volumetric features with coarse-to-fine implicit reconstructionOurs · Thuman2.0 test, full-bodyChamfer: 0.965 -> 0.798Improved
use generative volumetric features with coarse-to-fine implicit reconstructionOurs · Thuman2.0 test, full-bodyP2S: 0.848 -> 0.808Improved
use generative volumetric features with coarse-to-fine implicit reconstructionOurs · Thuman2.0 test, full-bodyNormal: 12.596 -> 12.441Hurt
add a coarse MLP to explicit voxel prediction (ablation)Ours - coarse MLP - fine MLP · Thuman2.0 testChamfer: 1.978 -> 0.818Improved
add a coarse MLP to explicit voxel prediction (ablation)Ours - coarse MLP - fine MLP · Thuman2.0 testP2S: 1.720 -> 0.926Improved
add a fine MLP with multiview normal fusion (ablation)Ours - fine MLP · Thuman2.0 testNormal PSNR: 10.704 -> 12.441Improved
add a fine MLP with multiview normal fusion (ablation)Ours - fine MLP · Thuman2.0 testP2S: 0.926 -> 0.808Improved
add a fine MLP with multiview normal fusion (ablation)Ours - fine MLP · Thuman2.0 testChamfer: 0.818 -> 0.798Improved
use ground-truth SMPL rather than fitted SMPL (ablation)Ours w/o GT SMPL · Thuman2.0 testChamfer: 1.224 -> 0.798Improved
use ground-truth SMPL rather than fitted SMPL (ablation)Ours w/o GT SMPL · Thuman2.0 testP2S: 1.062 -> 0.808Improved

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