Research map / Image generation / Text-to-image diffusion
DoodleFormer: Creative Sketch Drawing with Transformers
Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Jorma Laaksonen, Michael Felsberg
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 changed | Where | Measured | Effect |
|---|---|---|---|
| two-stage coarse-to-fine framework instead of single-stage (ablation) | DoodleFormer · Creative Birds | FID: 46.45 -> 20.14 | Improved |
| add GAT blocks to two-stage baseline (ablation) | DoodleFormer · Creative Birds | FID: 20.14 -> 16.89 | Improved |
| add GAT blocks to two-stage baseline (ablation) | DoodleFormer · Creative Birds | GD: 17.05 -> 17.16 | No clear effect |
| add GMM-based probabilistic box modelling (ablation) | DoodleFormer · Creative Birds | GD: 17.16 -> 18.33 | Improved |
| add GMM-based probabilistic box modelling (ablation) | DoodleFormer · Creative Birds | FID: 16.89 -> 16.45 | Improved |
| GAT layers instead of GCN layers in encoders (ablation) | DoodleFormer · Creative Birds | FID: 27.45 -> 16.45 | Improved |
| GAT layers instead of plain transformer layers (ablation) | DoodleFormer · Creative Birds | FID: 20.14 -> 16.45 | Improved |
| Mesh Graphormer (serial transformer+GCN) instead of plain transformer layers (ablation) | DoodleFormer · Creative Birds | FID: 20.14 -> 20.34 | No clear effect |
| DoodleFormer vs DoodlerGAN | DoodleFormer · Creative Birds | FID: 39.95 -> 16.45 | Improved |
| DoodleFormer vs DoodlerGAN on characteristic score | DoodleFormer · Creative Birds | CS: 0.69 -> 0.55 | Hurt |
| DoodleFormer vs DoodlerGAN | DoodleFormer · Creative Creatures | SDS: 1.45 -> 1.78 | Improved |
| DoodleFormer vs DoodlerGAN | DoodleFormer · Creative Creatures | FID: 43.94 -> 18.71 | Improved |
Later papers that compared with this method
2 later accepted papers report Doodleformer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion (AAAI 2026 · better on 2 of 3 shared results)
- VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation (ICCV 2025 · better on 6 of 6 shared results)
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.
- AttnGAN — AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks (CVPR 2018) · better on 1 of 1 shared result
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
- FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations (CVPR 2025 · similarity 0.88)
- SketchINR: A First Look into Sketches as Implicit Neural Representations (CVPR 2024 · similarity 0.87)
- It's All About Your Sketch: Democratising Sketch Control in Diffusion Models (CVPR 2024 · similarity 0.87)
- SketchAgent: Language-Driven Sequential Sketch Generation (CVPR 2025 · similarity 0.87)
- Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models (NeurIPS 2024 · similarity 0.87)
- AirSketch: Generative Motion to Sketch (NeurIPS 2024 · similarity 0.87)
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.
