SR-Ground: Image Quality Grounding for Super-Resolved Content
For researchers in super-resolution and image quality assessment, this dataset enables fine-grained artifact analysis and interpretable quality metrics, addressing a gap in existing holistic IQA methods.
SR-Ground introduces a large-scale dataset of 63,000 super-resolved images with pixel-level annotations for 6 artifact types, validated by 1,062 participants. Training IQA models with grounding on this dataset improves downstream task performance and enables artifact reduction in SR outputs.
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.