Research map / Image generation / Autoregressive and latent generation
AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add influence layer and CNN autoencoder and conditioning to Sketch-RNN | Conditional Sketch-RNN · FaceX | user-rated sketch quality: 3.9 avg rating, all p < .01 vs baselines | Helped |
| add influence layer and CNN autoencoder (each alone vs both) (ablation) | AI-Sketcher · FaceX | sketch quality (qualitative) | Helped |
| use AI-Sketcher instead of Sketch-RNN and Sketch-pix2seq as number of classes grows (5 to 20) | QuickDraw subsets · QuickDraw multi-class | total loss / quality | Helped |
| use AI-Sketcher instead of Sketch-RNN | QuickDraw, 5 categories · generation diversity (perceptual hash distance) | avg pairwise distance | No clear effect |
Closest papers by meaning
- A Neural Representation of Sketch Drawings (ICLR 2018 · similarity 0.89)
- SketchEmbedNet: Learning Novel Concepts by Imitating Drawings (ICML 2021 · similarity 0.88)
- SketchINR: A First Look into Sketches as Implicit Neural Representations (CVPR 2024 · similarity 0.88)
- SketchAgent: Language-Driven Sequential Sketch Generation (CVPR 2025 · similarity 0.87)
- It's All About Your Sketch: Democratising Sketch Control in Diffusion Models (CVPR 2024 · similarity 0.87)
- SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation (ICML 2025 · similarity 0.86)
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.