AI Paper Atlas

Research map / 3D vision / Face and shape

PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior

Seunggwan Lee, Hwanhee Jung, Byoungsoo Koh, Qixing Huang, Sang Ho Yoon, Sangpil Kim

ICCV 2025 · 3D vision › Face and shape · approach: 3D shape generative modeling · 6 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 IndivGCN (ablation)PASTA baseline · AmateurSketch-3DFID: 169.2 -> 158.8Improved
add IndivGCN (ablation)PASTA baseline · ProSketch-3DFID: 157.9 -> 148.4Improved
add PartGCN (ablation)PASTA baseline · AmateurSketch-3DFID: 169.2 -> 163.1Improved
add PartGCN (ablation)PASTA baseline · ProSketch-3DFID: 157.9 -> 152.0Improved
combine IndivGCN and PartGCN as ISG-Net (ablation)PASTA baseline · ProSketch-3DFID: 148.4 -> 129.2Improved
add text-aligned prior from VLM (ablation)PASTA baseline · ProSketch-3DFID: 157.9 -> 135.5Improved
add text-aligned prior on top of ISG-Net (full PASTA) (ablation)PASTA baseline · ProSketch-3DFID: 129.2 -> 112.2Improved
add ISG-Net on top of text prior (full PASTA) (ablation)PASTA baseline · AmateurSketch-3DCD: 0.101 -> 0.090Improved
sequential instead of parallel text-visual cross-attention (ablation)PASTA baseline · ProSketch-3DFID: 120.7 -> 112.2Improved
use LLaVA-7B instead of CLIP as VLM (ablation)PASTA baseline · AmateurSketch-3DFID: 152.1 -> 143.9Improved
use LLaVA-7B instead of BLIP2 T5 (ablation)PASTA baseline · ProSketch-3DFID: 115.6 -> 112.2Improved
use LLaVA-7B instead of LLaVA-13B (ablation)PASTA baseline · AmateurSketch-3DFID: 144.3 -> 143.9No clear effect

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