AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

Nan Bao, Yifan Zhao, Wenzhuang Wang, Jia Li

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Layout generation · 0 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 Semantic Anchoring, Primitive Imbuing and Conceptual Steering together (ablation)layout-to-image SD1.5 baseline · DIOR 5-shotBootstrap FID: 94.96 -> 74.34Improved
add Conceptual Steering on top of SA and PI (ablation)SA + PI model · DIOR 5-shotBootstrap FID: 85.00 -> 74.34Improved
add Conceptual Steering on top of SA and PI (ablation)SA + PI model · DIOR 5-shotmAP: 25.28 -> 26.06Improved
enable SA or PI individually and then combine them (ablation)SD1.5 baseline · DIOR 5-shotBootstrap FID: 94.96 -> 85.00 (SA+PI)Improved
use full number of SA injection layers rather than reduced (ablation)Ours full model · DIOR 5-shotmAP: 17.31 -> 26.06Improved
use full number of PI injection layers rather than reduced (ablation)Ours full model · DIOR 5-shotBootstrap FID: 76.48 -> 74.34Improved
keep SA in middle/early and PI in late upsampling blocks rather than swapping them (ablation)Ours full model · DIOR 5-shotmAP: 11.89 -> 26.06Improved
learn primitives with ridge-regression alternating optimization instead of random init (ablation)Primitive Imbuing · DIOR 5-shotBootstrap FID: 75.08 -> 74.34Improved
learn primitives with ridge-regression alternating optimization instead of fixed K-means (ablation)Primitive Imbuing · DIOR 5-shotBootstrap FID: 78.23 -> 74.34Improved
vary number of visual primitives (32, 64, 256 vs 128) (ablation)Primitive Imbuing · DIOR 5-shotBootstrap FID: 76.38 (32), 76.03 (64), 74.34 (128), 76.30 (256)Mixed
use proposed method vs CC-Diff on aerial domainOurs · DIOR 5-shotBootstrap FID: 82.51 -> 74.34Improved
evaluate with YOLOv8 detector instead of Faster R-CNNOurs vs CC-Diff · DIOR 5-shotmAP: 19.50 -> 20.80Improved

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