{"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/high-resolution-image-harmonization-via","title":"High-Resolution Image Harmonization via Collaborative Dual Transformations","arxiv_id":"2109.06671","date":"2021-09-14","proceeding":"CVPR 2022 1","authors":["Wenyan Cong","Xinhao Tao","Li Niu","Jing Liang","Xuesong Gao","Qihao Sun","Liqing Zhang"],"abstract":"Given a composite image, image harmonization aims to adjust the foreground to make it compatible with the background. High-resolution image harmonization is in high demand, but still remains unexplored. Conventional image harmonization methods learn global RGB-to-RGB transformation which could effortlessly scale to high resolution, but ignore diverse local context. Recent deep learning methods learn the dense pixel-to-pixel transformation which could generate harmonious outputs, but are highly constrained in low resolution. In this work, we propose a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel-to-pixel transformation and RGB-to-RGB transformation coherently in an end-to-end network. Our CDTNet consists of a low-resolution generator for pixel-to-pixel transformation, a color mapping module for RGB-to-RGB transformation, and a refinement module to take advantage of both. Extensive experiments on high-resolution benchmark dataset and our created high-resolution real composite images demonstrate that our CDTNet strikes a good balance between efficiency and effectiveness. Our used datasets can be found in https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization.","url_abs":"https://arxiv.org/abs/2109.06671v2","url_pdf":"https://arxiv.org/pdf/2109.06671v2.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":"high-resolution-image-harmonization-via","repo_url":"https://github.com/bcmi/CDTNet-High-Resolution-Image-Harmonization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-harmonization","task_name":"Image Harmonization"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-harmonization-on-hadobe5k-1024-times","task":"Image Harmonization","dataset":"HAdobe5k(1024$\\times$1024)","model":"CDTNet","rank_in_archive_order":3,"of":7,"metrics":{"MSE":"21.24","PSNR":"38.77","SSIM":"0.9868","fMSE":"152.13"},"uses_additional_data":false},{"leaderboard":"/sota/image-harmonization-on-iharmony4","task":"Image Harmonization","dataset":"iHarmony4","model":"CDTNet","rank_in_archive_order":6,"of":16,"metrics":{"MSE":"23.75","PSNR":"38.23","fMSE":"-"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.06671","atlas_url":"https://app.syntology.ai/?focus=2109.06671","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}