AI Paper Atlas

Research map / 3D vision / 3D generation

Sketch2CT: Multimodal Diffusion for Structure-Aware 3D Medical Volume Generation

Delin An, Chaoli Wang

CVPR 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 1 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 TSFE text-guided sketch feature extractor (ablation)Sketch2CT · CHAOS liver (CT) downstream segmentationDice: 0.864 -> 0.893Improved
add TSFE text-guided sketch feature extractor (ablation)Sketch2CT · Decathlon heart (MRI) downstream segmentationDice: 0.683 -> 0.711Improved
add CGFM cross-modal global fusion (ablation)Sketch2CT · CHAOS liver (CT) downstream segmentationDice: 0.825 -> 0.893Improved
add CGFM cross-modal global fusion (ablation)Sketch2CT · Decathlon heart (MRI) downstream segmentationDice: 0.671 -> 0.711Improved
add segmentation latent diffusion model for mask generation (ablation)Sketch2CT · CHAOS liver (CT) downstream segmentationDice: 0.642 -> 0.893Improved
add segmentation latent diffusion model for mask generation (ablation)Sketch2CT · Decathlon heart (MRI) downstream segmentationDice: 0.545 -> 0.711Improved
combine sketch and text conditioning instead of sketch-only or text-only (ablation)Sketch2CT · 3D mask generation (qualitative)mask qualityImproved
increase sketch granularity from coarse to fine (ablation)Sketch2CT · mask generationDice difference: 0.06 ± 0.02No clear effect
use Sketch2CT instead of Seg-DiffSketch2CT · Decathlon liver (CT) FIDFID: 34.8 -> 36.5Hurt
use Sketch2CT instead of Seg-DiffSketch2CT · CHAOS liver (CT) FIDFID: 37.8 -> 33.7Improved
use Sketch2CT instead of MedGen3DSketch2CT · Decathlon heart (MRI) FIDFID: 96.8 -> 65.1Improved
use Sketch2CT instead of Seg-DiffSketch2CT · Decathlon liver (CT) downstream segmentationDice: 0.887 -> 0.904Improved

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