AI Paper Atlas

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

Masked Region Transformer for Layered Image Generation and Editing at Scale

Zhicong Tang, Jingye Chen, Zhao Zhang, Mohan Zhou, Yuchi Liu, Yifan Pu, Yalong Bai, Ethan Smith, Yuhui Yuan

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control

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
scale backbone from FLUX.1 dev 13B to Qwen-Image 20B (ablation)MRT text-to-layers · 0.5M subsetFID_merged: 17.79 -> 16.15Improved
scale training data from 0.5M to 10M samples (ablation)MRT text-to-layers · T2LFID_merged: 16.15 -> 15.63Improved
add overflow data and canvas layer (ablation)MRT text-to-layers · T2L 0.5M subsetFID_merged: 15.68 -> 16.15 FID; PSNR 21.81 -> 22.75; SSIM 0.8543 -> 0.8711Mixed
add image-to-layers task to joint training (80/20/0) (ablation)MRT · T2L metricsFID_merged: 16.15 -> 15.68Improved
add layers-to-layers task to joint training (70/15/15) (ablation)MRT · T2L metricsFID_merged: 15.68 -> 17.06Hurt
add global text caption condition to image-to-layers (ablation)MRT image-to-layers · Design-Multi-Layer-BenchPSNR_layer: 26.03 -> 27.24Improved
add layer grouping augmentation (ablation)MRT image-to-layers · Design-Multi-Layer-BenchPSNR_merged: 21.65 -> 21.97Improved
add layer grouping augmentation (ablation)MRT image-to-layers · Design-Multi-Layer-BenchPSNR_layer: 27.24 -> 26.96No clear effect
distill with DMD2 from 50 to 16 steps (ablation)MRT text-to-layers · T2LFID_merged: 16.02 -> 16.21No clear effect
distill with DMD2 from 50 to 8 steps (ablation)MRT text-to-layers · T2LFID_merged: 16.02 -> 18.58Hurt
train on mixed short and long captions instead of one type (ablation)MRT text-to-layers · T2LFID_merged: short-only on long eval 18.56 -> mixed 15.93Improved
use MRT instead of Qwen-Image-Layered for image-to-layersimage-to-layers · OOD 100 designs, 16-32 layersPSNR_merged: 22.1828 -> 25.7229Improved

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