{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/plug-and-play-tri-branch-invertible-block-for","title":"Plug-and-Play Tri-Branch Invertible Block for Image Rescaling","arxiv_id":"2412.13508","date":"2024-12-18","proceeding":null,"authors":["Jingwei Bao","Jinhua Hao","Pengcheng Xu","Ming Sun","Chao Zhou","Shuyuan Zhu"],"abstract":"High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details. Recent advancements in image rescaling algorithms have employed invertible neural networks (INNs) to create a unified framework for downscaling and upscaling, ensuring a one-to-one mapping between LR and HR images. Traditional methods, utilizing dual-branch based vanilla invertible blocks, process high-frequency and low-frequency information separately, often relying on specific distributions to model high-frequency components. However, processing the low-frequency component directly in the RGB domain introduces channel redundancy, limiting the efficiency of image reconstruction. To address these challenges, we propose a plug-and-play tri-branch invertible block (T-InvBlocks) that decomposes the low-frequency branch into luminance (Y) and chrominance (CbCr) components, reducing redundancy and enhancing feature processing. Additionally, we adopt an all-zero mapping strategy for high-frequency components during upscaling, focusing essential rescaling information within the LR image. Our T-InvBlocks can be seamlessly integrated into existing rescaling models, improving performance in both general rescaling tasks and scenarios involving lossy compression. Extensive experiments confirm that our method advances the state of the art in HR image reconstruction.","url_abs":"https://arxiv.org/abs/2412.13508v1","url_pdf":"https://arxiv.org/pdf/2412.13508v1.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":"plug-and-play-tri-branch-invertible-block-for","repo_url":"https://github.com/jingwei-bao/t-invblocks","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Compressed Image Super-resolution"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-rescaling","task_name":"Image Rescaling"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-rescaling-on-bsd100-2x","task":"Image Rescaling","dataset":"BSD100-2x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"42.68","SSIM":"0.9913"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-bsd100-4x","task":"Image Rescaling","dataset":"BSD100-4x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"31.64","SSIM":"0.8837"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-2x","task":"Image Rescaling","dataset":"DIV2K val-2x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"45.46","SSIM":"0.9932"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-4x","task":"Image Rescaling","dataset":"DIV2K val-4x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"35.10","SSIM":"0.9328"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q30-2x","task":"Image Rescaling","dataset":"DIV2K val-q30-2x","model":"T-SAIN","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"31.89","SSIM":"0.8912"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q30-4x","task":"Image Rescaling","dataset":"DIV2K val-q30-4x","model":"T-SAIN","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"28.08","SSIM":"0.7893"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q50-2x","task":"Image Rescaling","dataset":"DIV2K val-q50-2x","model":"T-SAIN","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"33.71","SSIM":"0.9210"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q50-4x","task":"Image Rescaling","dataset":"DIV2K val-q50-4x","model":"T-SAIN","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"29.43","SSIM":"0.8237"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q70-2x","task":"Image Rescaling","dataset":"DIV2K val-q70-2x","model":"T-SAIN","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"35.20","SSIM":"0.9384"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q70-4x","task":"Image Rescaling","dataset":"DIV2K val-q70-4x","model":"T-SAIN","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"30.34","SSIM":"0.8421"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q90-2x","task":"Image Rescaling","dataset":"DIV2K val-q90-2x","model":"T-SAIN","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"36.30","SSIM":"0.9478"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q90-4x","task":"Image Rescaling","dataset":"DIV2K val-q90-4x","model":"T-SAIN","rank_in_archive_order":1,"of":4,"metrics":{"PSNR":"30.92","SSIM":"0.8517"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set14-2x","task":"Image Rescaling","dataset":"Set14-2x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"41.70","SSIM":"0.9809"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set14-4x","task":"Image Rescaling","dataset":"Set14-4x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"32.70","SSIM":"0.9003"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set5-2x","task":"Image Rescaling","dataset":"Set5-2x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"44.86","SSIM":"0.9883"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set5-4x","task":"Image Rescaling","dataset":"Set5-4x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"36.29","SSIM":"0.9452"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-urban100-2x","task":"Image Rescaling","dataset":"Urban100-2x","model":"T-IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"41.05","SSIM":"0.9899"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-urban100-4x","task":"Image Rescaling","dataset":"Urban100-4x","model":"T-IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"31.19","SSIM":"0.9132"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.13508","atlas_url":"https://app.syntology.ai/?focus=2412.13508","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2412.13508"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.13508\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.13508"},"call":"get_concepts_for_paper(arxiv_id=\"2412.13508\")"}],"by_repo":[{"repo":"jingwei-bao/t-invblocks","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"92b516322daea239b1150980dc3b2a97e5554c9fb6b6889e451d788f116f9654","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}