{"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/multi-field-de-interlacing-using-deformable","title":"Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention","arxiv_id":"2209.10192","date":"2022-09-21","proceeding":null,"authors":["Ronglei Ji","A. Murat Tekalp"],"abstract":"Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing network, which adapts the state-of-the-art superresolution approaches to the deinterlacing task. Our model aligns features from adjacent fields to a reference field (to be deinterlaced) using both deformable convolution residual blocks and self attention. Our extensive experimental results demonstrate that the proposed method provides state-of-the-art deinterlacing results in terms of both numerical and perceptual performance. At the time of writing, our model ranks first in the Full FrameRate LeaderBoard at https://videoprocessing.ai/benchmarks/deinterlacer.html","url_abs":"https://arxiv.org/abs/2209.10192v1","url_pdf":"https://arxiv.org/pdf/2209.10192v1.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":[],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"video-deinterlacing","task_name":"Video Deinterlacing"},{"task_slug":"video-restoration","task_name":"Video Restoration"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-deinterlacing-on-msu-deinterlacer","task":"Video Deinterlacing","dataset":"MSU Deinterlacer Benchmark","model":"DfRes (SA)","rank_in_archive_order":3,"of":31,"metrics":{"FPS on CPU":"0.1","PSNR":"43.486","SSIM":"0.972","Subjective":"0.925","VMAF":"95.96"},"uses_additional_data":false},{"leaderboard":"/sota/video-deinterlacing-on-msu-deinterlacer","task":"Video Deinterlacing","dataset":"MSU Deinterlacer Benchmark","model":"DfRes","rank_in_archive_order":4,"of":31,"metrics":{"FPS on CPU":"0.4","PSNR":"40.590","SSIM":"0.971","Subjective":"0.912","VMAF":"95.20"},"uses_additional_data":false},{"leaderboard":"/sota/video-deinterlacing-on-msu-deinterlacer","task":"Video Deinterlacing","dataset":"MSU Deinterlacer Benchmark","model":"DfRes (122000 G2e 3)","rank_in_archive_order":6,"of":31,"metrics":{"PSNR":"43.200","SSIM":"0.972","Subjective":"0.862","VMAF":"95.68"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}