AI Paper Atlas

Research map / 3D vision / Face and shape

Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images

Heming Zhu, Lingteng Qiu, Yuda Qiu, Xiaoguang Han

CVPR 2022 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 37 citations (OpenAlex)

Check 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
Register explicit garment templates to pixel-aligned implicit clothed-human fieldsReEF · Synthetic testing setCD (×10⁻³): 0.9725 -> 0.5477Improved
Add curve-aligned heatmap guidance to boundary-field generation (ablation)ReEF boundary-field generation · Garment boundary generationCD (×10⁻³): 6.3786 -> 1.1073Improved
Replace the proposed boundary fields with Point Transformer parsing of dense point cloudsGarment boundary generation · Garment boundary generationCD (×10⁻³): 1.1073 -> 6.5329Hurt
Replace the proposed boundary fields with image-guided graph convolution curve regressionGarment boundary generation · Garment boundary generationCD (×10⁻³): 1.1073 -> 9.18467Hurt
Remove pose initialization (ablation)ReEF explicit fitting · Garment mesh registrationDist (×10⁻³): 3.41651 -> 3.52109Hurt
Remove boundary initialization (ablation)ReEF explicit fitting · Garment mesh registrationDist (×10⁻³): 3.41651 -> 70.3211Hurt
Remove active area probing (ablation)ReEF explicit fitting · Garment mesh registrationDist (×10⁻³): 3.41651 -> 3.56883Hurt
Use only pixel-aligned coarse shape features for boundary generation (ablation)ReEF boundary-field generation · Garment boundary generationCD (×10⁻³): 1.1073 -> 6.3786Hurt

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