2020/06/15 by Orly Liba, Longqi Cai, Liba, Orly +14
Computer Science · Engineering · #Advanced Image Fusion Techniques #Advanced Vision and Imaging #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Filter (signal processing) #Geography #Graphics (cs.GR) #Image (mathematics) #Image Enhancement Techniques #Infrared Target Detection Methodologies #Noise (video) #Remote sensing #Sky #Upsampling #cs.CV #cs.GR
paper · pdf · doi:10.48550/arxiv.2006.10172
published in arXiv (Cornell University) (Cornell University) · Published in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2020
arxiv created 2020/06/15 · openalex publication_date 2020/06/15 · arxiv updated 2020/06/19 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
The sky is a major component of the appearance of a photograph, and its color\nand tone can strongly influence the mood of a picture. In nighttime\nphotography, the sky can also suffer from noise and color artifacts. For this\nreason, there is a strong desire to process the sky in isolation from the rest\nof the scene to achieve an optimal look. In this work, we propose an automated\nmethod, which can run as a part of a camera pipeline, for creating accurate sky\nalpha-masks and using them to improve the appearance of the sky. Our method\nperforms end-to-end sky optimization in less than half a second per image on a\nmobile device. We introduce a method for creating an accurate sky-mask dataset\nthat is based on partially annotated images that are inpainted and refined by\nour modified weighted guided filter. We use this dataset to train a neural\nnetwork for semantic sky segmentation. Due to the compute and power constraints\nof mobile devices, sky segmentation is performed at a low image resolution. Our\nmodified weighted guided filter is used for edge-aware upsampling to resize the\nalpha-mask to a higher resolution. With this detailed mask we automatically\napply post-processing steps to the sky in isolation, such as automatic\nspatially varying white-balance, brightness adjustments, contrast enhancement,\nand noise reduction.\n