{"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/deep-image-harmonization-in-dual-color-spaces","title":"Deep Image Harmonization in Dual Color Spaces","arxiv_id":"2308.02813","date":"2023-08-05","proceeding":null,"authors":["Linfeng Tan","Jiangtong Li","Li Niu","Liqing Zhang"],"abstract":"Image harmonization is an essential step in image composition that adjusts the appearance of composite foreground to address the inconsistency between foreground and background. Existing methods primarily operate in correlated $RGB$ color space, leading to entangled features and limited representation ability. In contrast, decorrelated color space (e.g., $Lab$) has decorrelated channels that provide disentangled color and illumination statistics. In this paper, we explore image harmonization in dual color spaces, which supplements entangled $RGB$ features with disentangled $L$, $a$, $b$ features to alleviate the workload in harmonization process. The network comprises a $RGB$ harmonization backbone, an $Lab$ encoding module, and an $Lab$ control module. The backbone is a U-Net network translating composite image to harmonized image. Three encoders in $Lab$ encoding module extract three control codes independently from $L$, $a$, $b$ channels, which are used to manipulate the decoder features in harmonization backbone via $Lab$ control module. Our code and model are available at \\href{https://github.com/bcmi/DucoNet-Image-Harmonization}{https://github.com/bcmi/DucoNet-Image-Harmonization}.","url_abs":"https://arxiv.org/abs/2308.02813v1","url_pdf":"https://arxiv.org/pdf/2308.02813v1.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":"deep-image-harmonization-in-dual-color-spaces","repo_url":"https://github.com/bcmi/duconet-image-harmonization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-harmonization","task_name":"Image Harmonization"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-harmonization-on-hadobe5k-1024-times","task":"Image Harmonization","dataset":"HAdobe5k(1024$\\times$1024)","model":"DucoNet","rank_in_archive_order":1,"of":7,"metrics":{"MSE":"10.94","PSNR":"41.37","SSIM":"0.9886","fMSE":"80.69"},"uses_additional_data":false},{"leaderboard":"/sota/image-harmonization-on-iharmony4","task":"Image Harmonization","dataset":"iHarmony4","model":"DucoNet","rank_in_archive_order":3,"of":16,"metrics":{"MSE":"18.47","PSNR":"39.17","fMSE":"212.53"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.02813","atlas_url":"https://app.syntology.ai/?focus=2308.02813","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}