AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

Songhua Liu, Jingwen Ye, Sucheng Ren, Xinchao Wang

ECCV 2022 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 45 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 dynamic attention pruning (ablation)DynaST · DeepFashion (pose-guided generation)FID: 9.32 -> 8.36Improved
add dynamic attention pruning (ablation)DynaST · DeepFashion (pose-guided generation)SWD: 21.8 -> 11.8Improved
add dynamic attention pruning (ablation)DynaST · CelebA-HQ (edge-guided face synthesis)FID: 15.3 -> 12.0Improved
add inner-scale sparse attention blocks (ablation)DynaST · DeepFashion (pose-guided generation)FID: 8.88 -> 8.36Improved
add inner-scale sparse attention blocks (ablation)DynaST · CelebA-HQ (edge-guided face synthesis)FID: 14.7 -> 12.0Improved
raise matching resolution from 32 to full 256 (ablation)DynaST · DeepFashion (pose-guided generation)FID: 8.55 -> 8.36Improved
raise matching resolution from 64 to full 256 (ablation)DynaST · DeepFashion warped vs ground truthL1: 0.063 -> 0.054Improved
raise matching resolution from 128 to full 256 (ablation)DynaST · DeepFashion (pose-guided generation)FID: 8.41 -> 8.36Improved
raise matching resolution from 32 to full 256 (ablation)DynaST · DeepFashion warped vs ground truthTime (x1e-2 s): 5.53 -> 9.63Hurt
use dynamic sparse attention instead of CoCosNet-v2 recurrent GRU matchingexemplar-guided generation · DeepFashion warped vs ground truthTime (x1e-2 s): 21.7 -> 9.63Improved
use DynaST instead of CoCosNet-v2exemplar-guided generation · DeepFashion (pose-guided generation)FID: 13.0 -> 8.36Improved

Later papers that compared with this method

2 later accepted papers report DynaST as a baseline in their results tables; 1 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