AI Paper Atlas

Research map / 3D vision / Face and shape

CLOTH4D: A Dataset for Clothed Human Reconstruction

Xingxing Zou, Xintong Han, Waikeung Wong

CVPR 2023 · 3D vision › Face and shape · approach: Clothed human modeling · 25 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
Retrain PIFu on CLOTH4D rather than its original scan training dataPIFu · CLOTH4D testChamfer ↓: 3.578 -> 2.412Improved
Retrain ICON on CLOTH4D rather than its original scan training dataICON · CLOTH4D testChamfer ↓: 4.196 -> 3.499Improved
Retrain PIFu on CLOTH4D rather than its original scan training dataPIFu · CAPE testChamfer ↓: 4.204 -> 4.381Hurt
Retrain ICON on CLOTH4D rather than its original scan training dataICON · CAPE testChamfer ↓: 3.962 -> 3.544Hurt
Use ground-truth SMPL fits instead of estimated SMPLICON · CLOTH4D testChamfer ↓: 4.196 -> 1.631Improved
Use ground-truth SMPL fits instead of estimated SMPLPaMIR · CLOTH4D testChamfer ↓: 4.157 -> 2.487Improved
Add a temporal term penalizing Chamfer distance between successive frames (ablation)PIFuclo · CLOTH4D testChamferddt ↓: 0.157→0.123Improved
Add a temporal term penalizing Chamfer distance between successive frames (ablation)PIFuclo · CLOTH4D testChamferdtd ↓: 0.546→0.454Improved
Use CLOTH4D-trained models instead of original modelsPIFu and PaMIR · CLOTH4D testreconstruction quality: PIFu P2S: 3.911 -> 2.793; PaMIR P2S: 3.827 -> 5.037Mixed
Use ground-truth SMPL fits instead of estimated SMPLICON · CLOTH4D testNormalsddt ↓: 0.013 -> 0.030Hurt

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