AI Paper Atlas

Research map / 3D vision / Face and shape

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Zechuan Zhang, Li Sun, Zongxin Yang, Ling Chen, Yi Yang

NeurIPS 2023 · 3D vision › Face and shape · approach: Clothed human modeling · 8 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
replace transformer with UNet convolution (ablation)GTA · CAPEChamfer: 0.861 -> 0.991Hurt
remove cross-attention and learnable embeddings (ablation)GTA · CAPEChamfer: 0.861 -> 0.937Hurt
remove refinement module (ablation)GTA · CAPEChamfer: 0.861 -> 0.890Hurt
use 2D features with spatial query instead of 3D (ablation)GTA · CAPEChamfer: 0.861 -> 1.054Hurt
use 2D features with prior-enhanced query (ablation)GTA · CAPEChamfer: 0.861 -> 1.133Hurt
use 2D features with hybrid fusion (ablation)GTA · CAPEChamfer: 0.861 -> 1.008Hurt
3D features with spatial query only (no hybrid prior fusion) (ablation)GTA · CAPEChamfer: 0.861 -> 0.987Hurt
3D features with prior-enhanced query only (ablation)GTA · CAPEChamfer: 0.861 -> 1.059Hurt
spatial query vs prior-enhanced query (ablation)GTA · CAPEChamfer: 1.059 -> 0.987Improved
GTA vs ECON on THuman2.0GTA · THuman2.0Chamfer: 2.120 -> 0.814Improved
GTA vs ECON on CAPE normalsGTA · CAPE-NFPNormals: 0.035 -> 0.042Hurt
GTA vs ICON on CAPE-FPGTA · CAPE-FPChamfer: 0.969 -> 0.763Improved

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