AI Paper Atlas

Research map / 3D vision / Face and shape

ShapeScaffolder: Structure-Aware 3D Shape Generation from Text

Xi Tian, Yong-Liang Yang, Qi Wu

ICCV 2023 · 3D vision › Face and shape · approach: 3D shape generative modeling · 15 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 flat decoder with hierarchical decoder (ablation)HierD · Level 1 outputIoU: 10.38 -> 11.20Improved
replace word-level attention with graph-part attention at Level 2 (ablation)HierD · Level 2 outputIoU: 11.66 -> 12.63Improved
add graph-part attention at Level 2 to base hierarchical decoder (ablation)HierD · Level 2 outputCLIP: 45.36 -> 50.64Improved
apply graph attention at Level 1 instead of Level 2 (ablation)HierD · Level 2 outputIoU: 12.63 -> 11.30Hurt
add joint refiner at Level 2 (ablation)HierD + GraphAttn · Level 2 outputIoU: 12.63 -> 13.65Improved
add joint refiner at Level 2 (ablation)HierD + GraphAttn · Level 2 outputFID: 16.31 -> 15.81Improved
add word-level attention at Level 2 (ablation)HierD · Level 2 outputIoU: 11.07 -> 11.66Improved
add hierarchical bond loss structure with deeper levels (ablation)HierD · Level 1 vs Level 2 outputIoU: 11.20 -> 11.07Hurt
structure-aware text-to-shape generation versus T2S-ImplicitShapeScaffolder · Text2Shape datasetAcc: 97.48 -> 97.5No clear effect

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