AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
use DiffSketcher instead of CLIPasso for text-prompt consistencyDiffSketcher · text-to-sketch evaluationCLIP cosine similarity: 0.3075 -> 0.3494Helped
use DiffSketcher instead of CLIPasso for aestheticsDiffSketcher · text-to-sketch evaluationCLIP aesthetic score: 4.0821 -> 4.8206Helped
use DiffSketcher instead of VectorFusion/CLIPassoDiffSketcher · User studyconfusion score: 0.39 -> 0.65Helped
initialize strokes from fused LDM attention maps instead of random or CLIP saliency (ablation)DiffSketcher · qualitative convergencesynthesis speed and qualityHelped
add ASDS loss to JVSP loss (ablation)DiffSketcher · qualitativedetail and diversityHelped
add stroke opacity optimization (ablation)DiffSketcher · qualitativevisual qualityHelped
vary data augmentation strategy (ablation)ASDS loss · qualitativequalityNo clear effect
change prompt keywords (sketch, drawing, photo) (ablation)DiffSketcher · qualitativesketch styleNo 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