AI Paper Atlas

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

Histogram-constrained Image Generation

Haoming Liu, Yuanhe Guo, Yijia Cao, Shenji Wan, Hongyi Wen

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 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
apply OT guidance during sampling instead of direct OT on the finished image (ablation)HIG color-constrained generation · Color-constrained generationCLIP-Score / Aesthetics: 26.94 -> 27.19 CLIP, 6.52 -> 6.78 AestheticsImproved
add guidance during sampling versus direct OT, histogram alignment (ablation)HIG · Color-constrained generationHistKL: 0.00 -> 1.09Mixed
add post-hoc OT after guided sampling (ablation)HIG (guidance) · Color-constrained generationHistKL: 1.09 -> 0.00Improved
add post-hoc OT after guided sampling (ablation)HIG (guidance) · Color-constrained generationCLIP-Score / Aesthetics: 27.19 -> 26.91 CLIP, 6.78 -> 6.66 AestheticsHurt
apply HIG color guidance versus unconstrained SDXL generationSDXL · Color-constrained generationHistKL: 10.87 -> 1.09Improved
apply HIG guidance versus unconstrained SDXL on prompt complianceSDXL · Color-constrained generationCLIP-Score: 29.47 -> 27.19Hurt
use multi-option binning instead of single-option binning for information embedding (ablation)HIG information embedding · Information embedding, 256 tokensexact match: 97.3% -> 97.7%Improved
use multi-option binning instead of single-option binning for information embedding (ablation)HIG information embedding · Information embedding, 512 tokensexact match: 91.0% -> 90.3%Hurt
increase embedded text from 32 to 512 tokens (ablation)HIG information embedding · Information embeddingexact match (single-option): 100.0% -> 91.0%Hurt
apply JPEG compression to embedded images (ablation)HIG information embedding · Robustnessexact match: below 90% once text exceeds 32 tokensHurt
apply random scaling [0.5, 2.0] to embedded images (ablation)HIG information embedding · Robustnessexact reconstruction rate: around 90% for text lengths up to 128 tokensNo clear effect

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