{"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/reconet-real-time-coherent-video-style","title":"ReCoNet: Real-time Coherent Video Style Transfer Network","arxiv_id":"1807.01197","date":"2018-07-03","proceeding":null,"authors":["Chang Gao","Derun Gu","Fangjun Zhang","Yizhou Yu"],"abstract":"Image style transfer models based on convolutional neural networks usually\nsuffer from high temporal inconsistency when applied to videos. Some video\nstyle transfer models have been proposed to improve temporal consistency, yet\nthey fail to guarantee fast processing speed, nice perceptual style quality and\nhigh temporal consistency at the same time. In this paper, we propose a novel\nreal-time video style transfer model, ReCoNet, which can generate temporally\ncoherent style transfer videos while maintaining favorable perceptual styles. A\nnovel luminance warping constraint is added to the temporal loss at the output\nlevel to capture luminance changes between consecutive frames and increase\nstylization stability under illumination effects. We also propose a novel\nfeature-map-level temporal loss to further enhance temporal consistency on\ntraceable objects. Experimental results indicate that our model exhibits\noutstanding performance both qualitatively and quantitatively.","url_abs":"http://arxiv.org/abs/1807.01197v2","url_pdf":"http://arxiv.org/pdf/1807.01197v2.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":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/EmptySamurai/pytorch-reconet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/LeMU-Haruka/reconet-mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/OfekCohen1/Style-On-3D-Video","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/irsisyphus/reconet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/liulai/reconet-torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/safwankdb/ReCoNet-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/xiuyu0000/papers_with_examples/tree/main/reconet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"reconet-real-time-coherent-video-style","repo_url":"https://github.com/yangyucheng000/ReCoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"video-style-transfer","task_name":"Video Style Transfer"}],"methods":[{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-fmb-dataset","task":"Semantic Segmentation","dataset":"FMB Dataset","model":"ReCoNet (RGB-Infrared)","rank_in_archive_order":8,"of":14,"metrics":{"mIoU":"50.90"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.01197","atlas_url":"https://app.syntology.ai/?focus=1807.01197","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}