为超分辨率图像的视觉伪影提供细粒度标注，提升质量评估与修复能力。
SR-Ground: Image Quality Grounding for Super-Resolved Content
- 构建63,000张图像的细粒度伪影分割数据集，涵盖6类常见伪影
- 基于该数据集训练的模型在下游任务中显著提升质量评估准确率
- 可指导超分辨模型优化，减少用户感知到的视觉瑕疵
近年来，基于扩散模型的超分辨率（SR）技术虽大幅提升了图像保真度，却引入了新型视觉伪影。现有图像质量评估（IQA）方法虽能给出整体评分，但缺乏可解释性，无法区分不同类型的伪影。为此，我们提出SR-Ground，一个大规模细粒度伪影分割数据集，包含由多种先进SR模型处理的图像，以及多类伪影的像素级标注。通过1,062名参与者的大规模众包研究，验证并优化了自动生成的分割结果，最终形成包含63,000张图像、覆盖6种不同伪影类型的数据集。实验证明，在SR-Ground上训练具备定位能力的IQA模型，能显著提升下游任务表现。此外，我们设计了一种微调流程，利用该定位模型有效降低超分辨输出中的感知伪影，充分体现了数据集的实用价值。
原文摘要 · Abstract (English)
Super-Resolution (SR) has advanced rapidly in recent years, with diffusion-based models achieving unprecedented fidelity at the cost of introducing new types of visual artifacts. While existing Image Quality Assessment (IQA) methods provide holistic quality scores, they lack interpretability and fail to distinguish between different artifact types arising from modern SR approaches. To address this gap, we introduce SR-Ground, a large-scale dataset specifically designed for fine-grained artifact segmentation in super-resolved images. The dataset comprises images processed by a diverse set of state-of-the-art SR models, with pixel-level annotations for multiple artifact categories. We conduct a large-scale crowdsourcing study involving 1,062 participants to validate and refine automatically generated segmentations, resulting in a high-quality dataset of 63,000 images spanning 6 distinct artifact types. We demonstrate that training IQA models with grounding capabilities on SR-Ground significantly improves performance on downstream tasks. Furthermore, we introduce a fine-tuning pipeline that leverages our grounding model to reduce perceptible artifacts in SR outputs, showcasing the practical utility of our dataset.
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。