构建108万图文对数据集，提升图像生成评价的全面性与精准度。
HPSv3: Towards Wide-Spectrum Human Preference Score
- 构建包含108万图文对的HPDv3数据集，覆盖真实世界图像与生成图像
- 基于视觉语言模型的评分模型，在117万对比数据上实现细粒度排序
- 提出迭代优化方法CoHP，无需新增数据即可提升生成图像质量
评估文生图模型需符合人类感知，但现有以人为核心的方法受限于数据覆盖不足、特征提取不佳及损失函数效率低。为此，我们提出人类偏好评分v3（HPSv3）：(1) 发布首个广谱人类偏好数据集HPDv3，整合108万文本-图像对和117万来自先进生成模型及真实世界高低质量图像的成对标注；(2) 提出基于视觉语言模型的偏好模型，采用不确定性感知的排序损失进行细粒度打分；同时提出链式人类偏好（CoHP）方法，通过HPSv3在每一步筛选最优图像，实现无需额外数据的迭代优化。大量实验表明，HPSv3可作为跨尺度图像评估的稳健指标，CoHP为高效且符合人类偏好的图像质量提升方案。代码与数据集已开放于HPSv3主页。
原文摘要 · Abstract (English)
Evaluating text-to-image generation models requires alignment with human perception, yet existing human-centric metrics are constrained by limited data coverage, suboptimal feature extraction, and inefficient loss functions. To address these challenges, we introduce Human Preference Score v3 (HPSv3). (1) We release HPDv3, the first wide-spectrum human preference dataset integrating 1.08M text-image pairs and 1.17M annotated pairwise comparisons from state-of-the-art generative models and low to high-quality real-world images. (2) We introduce a VLM-based preference model trained using an uncertainty-aware ranking loss for fine-grained ranking. Besides, we propose Chain-of-Human-Preference (CoHP), an iterative image refinement method that enhances quality without extra data, using HPSv3 to select the best image at each step. Extensive experiments demonstrate that HPSv3 serves as a robust metric for wide-spectrum image evaluation, and CoHP offers an efficient and human-aligned approach to improve image generation quality. The code and dataset are available at the HPSv3 Homepage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。