atlas

Research map / Image generation / Autoregressive and latent generation

Local Attention Pyramid for Scene Image Generation

CVPR 2022 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 6 citations (OpenAlex)

Check 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
Add Local Attention Pyramid (LAP) to StyleGANStyleGAN · COCO-stuffFID: 31.6 -> 30.7Helped
Add Local Attention Pyramid (LAP) to MSG-StyleGANMSG-StyleGAN · COCO-stuffFSD: 655.8 -> 563.1Helped
Add Local Attention Pyramid (LAP) to StyleGANStyleGAN · LSUN BedroomFID: 4.2 -> 3.4Helped
Add Local Attention Pyramid (LAP) to StyleGANStyleGAN · LSUN BedroomFSD: 38.4 -> 34.5Helped
Add Local Attention Pyramid (LAP) to MSG-DCGANMSG-DCGAN · LSUN CombinedFID: 81.4 -> 46.6Helped
Add channel-separated transformation and spatial attention (ablation)StyleGAN · LSUN BedroomFID: 6.5 -> 5.3Helped
Add local attention pyramid to the channel-separated transformation model (ablation)StyleGAN with Sec. 4.1 · LSUN BedroomFID: 5.3 -> 4.9Helped
Remove depthwise convolution layers and use single-channel spatial attention (ablation)StyleGAN with channel-separated transformation and spatial attention · LSUN BedroomFID: 5.3 -> 8.3Hurt

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