2021/05/19 by Jie Liang, Hui Zeng, Liang, Jie +7 · 13 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Art #Artificial intelligence #Benchmark (surveying) #Cartography #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Consistency (knowledge bases) #Construct (python library) #Engineering #FOS: Computer and information sciences #Geography #Image Enhancement Techniques #Information retrieval #Portrait #Raw data #Scale (ratio) #Segmentation #Set (abstract data type) #Task (project management) #Visual Attention and Saliency Detection #Visual arts #cs.CV
paper · pdf · doi:10.48550/arxiv.2105.09180
published in arXiv (Cornell University) (Cornell University) · To appear at CVPR 2021
arxiv created 2021/05/19 · openalex publication_date 2021/05/19 · arxiv updated 2021/05/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
Different from general photo retouching tasks, portrait photo retouching (PPR), which aims to enhance the visual quality of a collection of flat-looking portrait photos, has its special and practical requirements such as human-region priority (HRP) and group-level consistency (GLC). HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone. Models trained on existing general photo retouching datasets, however, can hardly meet these requirements of PPR. To facilitate the research on this high-frequency task, we construct a large-scale PPR dataset, namely PPR10K, which is the first of its kind to our best knowledge. PPR10K contains 1, 681 groups and 11, 161 high-quality raw portrait photos in total. High-resolution segmentation masks of human regions are provided. Each raw photo is retouched by three experts, while they elaborately adjust each group of photos to have consistent tones. We define a set of objective measures to evaluate the performance of PPR and propose strategies to learn PPR models with good HRP and GLC performance. The constructed PPR10K dataset provides a good benchmark for studying automatic PPR methods, and experiments demonstrate that the proposed learning strategies are effective to improve the retouching performance. Datasets and codes are available: https://github.com/csjliang/PPR10K.