Papers › HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation

HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation

10 May 2025arXiv:2505.06512archive 2025-07-28

Hang Wang, Zhi-Qi Cheng, Chenhao Lin, Chao Shen, Lei Zhang

Text-to-image synthesis has progressed to the point where models can generate visually compelling images from natural language prompts. Yet, existing methods often fail to reconcile high-level semantic fidelity with explicit spatial control, particularly in scenes involving multiple objects, nuanced relations, or complex layouts. To bridge this gap, we propose a Hierarchical Cross-Modal Alignment (HCMA) framework for grounded text-to-image generation. HCMA integrates two alignment modules into each diffusion sampling step: a global module that continuously aligns latent representations with textual descriptions to ensure scene-level coherence, and a local module that employs bounding-box layouts to anchor objects at specified locations, enabling fine-grained spatial control. Extensive experiments on the MS-COCO 2014 validation set show that HCMA surpasses state-of-the-art baselines, achieving a 0.69 improvement in Frechet Inception Distance (FID) and a 0.0295 gain in CLIP Score. These results demonstrate HCMA's effectiveness in faithfully capturing intricate textual semantics while adhering to user-defined spatial constraints, offering a robust solution for semantically grounded image generation. Our code is available at https://github.com/hwang-cs-ime/HCMA.

PaperPDFCode

Code

hwang-cs-ime/hcma officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationText to Image GenerationText-to-Image Generationcross-modal alignment

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPDiffusionSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections