AI Paper Atlas

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

ECCV 2022 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 31 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
two-stage coarse-to-fine framework instead of single-stage (ablation)DoodleFormer · Creative BirdsFID: 46.45 -> 20.14Improved
add GAT blocks to two-stage baseline (ablation)DoodleFormer · Creative BirdsFID: 20.14 -> 16.89Improved
add GAT blocks to two-stage baseline (ablation)DoodleFormer · Creative BirdsGD: 17.05 -> 17.16No clear effect
add GMM-based probabilistic box modelling (ablation)DoodleFormer · Creative BirdsGD: 17.16 -> 18.33Improved
add GMM-based probabilistic box modelling (ablation)DoodleFormer · Creative BirdsFID: 16.89 -> 16.45Improved
GAT layers instead of GCN layers in encoders (ablation)DoodleFormer · Creative BirdsFID: 27.45 -> 16.45Improved
GAT layers instead of plain transformer layers (ablation)DoodleFormer · Creative BirdsFID: 20.14 -> 16.45Improved
Mesh Graphormer (serial transformer+GCN) instead of plain transformer layers (ablation)DoodleFormer · Creative BirdsFID: 20.14 -> 20.34No clear effect
DoodleFormer vs DoodlerGANDoodleFormer · Creative BirdsFID: 39.95 -> 16.45Improved
DoodleFormer vs DoodlerGAN on characteristic scoreDoodleFormer · Creative BirdsCS: 0.69 -> 0.55Hurt
DoodleFormer vs DoodlerGANDoodleFormer · Creative CreaturesSDS: 1.45 -> 1.78Improved
DoodleFormer vs DoodlerGANDoodleFormer · Creative CreaturesFID: 43.94 -> 18.71Improved

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.

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