AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Anchored Unsigned Distance Functions With Gradient Direction Alignment for Single-View Garment Reconstruction

Fang Zhao, Wenhao Wang, Shengcai Liao, Ling Shao

ICCV 2021 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 54 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
add the gradient direction alignment loss L_GDA (ablation)AnchorUDF · MGNChamfer: 0.696 -> 0.635Improved
add the gradient direction alignment loss L_GDA (ablation)AnchorUDF · MGNP2S: 0.899 -> 0.762Improved
add the gradient direction alignment loss L_GDA (ablation)AnchorUDF · Deep Fashion3DChamfer: 0.712 -> 0.621Improved
add the gradient direction alignment loss L_GDA (ablation)AnchorUDF · Deep Fashion3DP2S: 0.932 -> 0.839Improved
use anchor-point position features instead of depth value (ablation)AnchorUDF · MGNChamfer: 1.063 -> 0.696Improved
use anchor-point position features instead of 3D coordinates (ablation)AnchorUDF · MGNP2S: 1.060 -> 0.899Improved
use anchor-point position features instead of depth value (ablation)AnchorUDF · Deep Fashion3DP2S: 2.440 -> 0.932Improved
use anchor-point position features instead of 3D coordinates (ablation)AnchorUDF · Deep Fashion3DChamfer: 1.062 -> 0.712Improved
increase anchor points from 100 to 600 (ablation)AnchorUDF · MGNChamfer: 0.731 -> 0.696Improved
increase anchor points from 600 to 900 (ablation)AnchorUDF · MGNChamfer: 0.696 -> 0.758Hurt
increase anchor points from 600 to 900 (ablation)AnchorUDF · MGNP2S: 0.899 -> 1.014Hurt
add the HD module with 1024x1024 inputAnchorUDF · Deep Fashion3DP2S: 0.839 -> 0.737Improved

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