AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

Zirui Zheng, Takashi Isobe, Tong Shen, XU JIA, Xiaomin Li, Jianbin Zhao, Mengmeng Ge, Baolu Li, Qinghe Wang, Haiwen Diao, Dong Li, Yunzhi Zhuge and 3 more

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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 GRPO post-training with HPS plus layout reward (ablation)SMARLI-SFT · LayoutSAM-EvalImageReward / mIoU: IR 60.88 -> 74.81; mIoU 80.08 -> 81.31Improved
use HPS reward alone in GRPO (ablation)SMARLI-SFT · LayoutSAM-EvalColor / mIoU: Color 86.17 -> 83.96; mIoU 80.08 -> 77.79Hurt
use layout reward alone in GRPO (ablation)SMARLI-SFT · LayoutSAM-EvalImageReward: 60.88 -> 58.34Hurt
drop detection score from layout reward (ablation)GRPO HPS+VQA · LayoutSAM-EvalPrecision: 81.84 -> 74.50Hurt
drop VQA score from layout reward (ablation)GRPO HPS+DET · LayoutSAM-EvalColor: 87.35 -> 85.61Hurt
allow layout tokens to attend to global prompt (vs w/o LP) (ablation)structured masking · LayoutSAM-Evalattribute controlImproved
use per-object causal, isolated layout masks and region-wise image attention (vs w/o Local Causal) (ablation)structured masking · LayoutSAM-Evalspatial metricsImproved
SMARLI vs PlanGenAR layout-to-image · OverLayBench-ComplexSR_E: 67.79 -> 80.52Improved
SMARLI vs PlanGen on FIDAR layout-to-image · LayoutSAM-EvalFID: 13.91 -> 18.16Hurt
add layout condition on top of Show-oShow-o · T2I-CompBenchSpatial: 39.6 -> 49.7Improved

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