{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/difar-deep-image-formation-and-retouching","title":"CURL: Neural Curve Layers for Global Image Enhancement","arxiv_id":"1911.13175","date":"2019-11-29","proceeding":null,"authors":["Sean Moran","Steven McDonagh","Gregory Slabaugh"],"abstract":"We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in three different colour spaces (HSV, CIELab, RGB) guided by a novel multi-colour space loss. The curves are fully differentiable and are trained end-to-end for different computer vision problems including photo enhancement (RGB-to-RGB) and as part of the image signal processing pipeline for image formation (RAW-to-RGB). To demonstrate the effectiveness of CURL we combine this global image transformation block with a pixel-level (local) image multi-scale encoder-decoder backbone network. In an extensive experimental evaluation we show that CURL produces state-of-the-art image quality versus recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple public datasets. Our code is publicly available at: https://github.com/sjmoran/CURL.","url_abs":"https://arxiv.org/abs/1911.13175v4","url_pdf":"https://arxiv.org/pdf/1911.13175v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"difar-deep-image-formation-and-retouching","repo_url":"https://github.com/sjmoran/CURL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"difar-deep-image-formation-and-retouching","repo_url":"https://github.com/sjmoran/difar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"difar-deep-image-formation-and-retouching","repo_url":"https://github.com/sjmoran/neural_curve_layers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"photo-retouching","task_name":"Photo Retouching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-enhancement-on-mit-adobe-5k","task":"Image Enhancement","dataset":"MIT-Adobe 5k","model":"DIFAR (MSCA, level 1)","rank_in_archive_order":10,"of":11,"metrics":{"PSNR on proRGB":"24.2","SSIM on proRGB":"0.88"},"uses_additional_data":false},{"leaderboard":"/sota/photo-retouching-on-mit-adobe-5k","task":"Photo Retouching","dataset":"MIT-Adobe 5k","model":"DIFAR\n(MSCA, level 1)","rank_in_archive_order":4,"of":5,"metrics":{"PSNR":"24.2","SSIM":"0.88"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.13175","atlas_url":"https://app.syntology.ai/?focus=1911.13175","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}