# BiDPO：基于区域感知双模态直接偏好优化的组合式文本到图像生成

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-27 08:00
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmpw15rrx03fkslukkrs88znx
- 原文链接：https://arxiv.org/abs/2605.28615

## AI 摘要

BiDPO是一种旨在增强文本到图像模型组合式生成能力的框架，用于更准确地反映包含属性绑定、对象关系和计数的复杂提示。该框架通过精心设计的流程构建了大规模偏好数据集BiComp，并扩展Diffusion DPO技术，联合优化图像与文本偏好。此外，采用区域级指导方法以聚焦于与组合概念相关的区域。实验结果表明，BiDPO在多个基准测试上显著提升了组合保真度，并持续优于现有方法。

## 正文

Despite the rapid progress of text-to-image (T2I) models, generating images that accurately reflect complex compositional prompts (covering attribute bindings, object relationships, counting) still remains challenging. To address this, we propose BiDPO, a framework to enhance T2I model's capability of compositional text-to-image generation. We begin by introducing an carefully designed pipeline to construct a large-scale preference dataset, BiComp, with strictly quality control. Then, we extend Diffusion DPO to jointly optimize image and text preferences, which is shown to greatly effective in improving the models to follow complex text prompt in generation. To further enhance the models for fine-grained alignment, we employ a region-level guidance method to focus on regions relevant to compositional concepts. Experimental results demonstrate that our BiDPO substantially improves compositional fidelity, consistently outperforming prior methods across multiple benchmarks. Our approach highlights the potential of preference-based fine-tuning for complex text-to-image tasks, offering a flexible and scalable alternative to existing techniques.