{"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/spatial-separated-curve-rendering-network-for","title":"Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization","arxiv_id":"2109.05750","date":"2021-09-13","proceeding":null,"authors":["Jingtang Liang","Xiaodong Cun","Chi-Man Pun","Jue Wang"],"abstract":"Image harmonization aims to modify the color of the composited region with respect to the specific background. Previous works model this task as a pixel-wise image-to-image translation using UNet family structures. However, the model size and computational cost limit the ability of their models on edge devices and higher-resolution images. To this end, we propose a novel spatial-separated curve rendering network(S$^2$CRNet) for efficient and high-resolution image harmonization for the first time. In S$^2$CRNet, we firstly extract the spatial-separated embeddings from the thumbnails of the masked foreground and background individually. Then, we design a curve rendering module(CRM), which learns and combines the spatial-specific knowledge using linear layers to generate the parameters of the piece-wise curve mapping in the foreground region. Finally, we directly render the original high-resolution images using the learned color curve. Besides, we also make two extensions of the proposed framework via the Cascaded-CRM and Semantic-CRM for cascaded refinement and semantic guidance, respectively. Experiments show that the proposed method reduces more than 90% parameters compared with previous methods but still achieves the state-of-the-art performance on both synthesized iHarmony4 and real-world DIH test sets. Moreover, our method can work smoothly on higher resolution images(eg., $2048\\times2048$) in 0.1 seconds with much lower GPU computational resources than all existing methods. The code will be made available at \\url{http://github.com/stefanLeong/S2CRNet}.","url_abs":"https://arxiv.org/abs/2109.05750v4","url_pdf":"https://arxiv.org/pdf/2109.05750v4.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":"spatial-separated-curve-rendering-network-for","repo_url":"https://github.com/stefanleong/s2crnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spatial-separated-curve-rendering-network-for","repo_url":"https://github.com/vinthony/s2crnet-demos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-harmonization","task_name":"Image Harmonization"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"2048","task_name":"Playing the Game of 2048"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-harmonization-on-iharmony4","task":"Image Harmonization","dataset":"iHarmony4","model":"S2CRNet-VGG","rank_in_archive_order":12,"of":16,"metrics":{"MSE":"35.58","PSNR":"37.18","fMSE":"274.99"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.05750","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}