{"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/invertible-image-rescaling","title":"Invertible Image Rescaling","arxiv_id":"2005.05650","date":"2020-05-12","proceeding":"ECCV 2020 8","authors":["Mingqing Xiao","Shuxin Zheng","Chang Liu","Yaolong Wang","Di He","Guolin Ke","Jiang Bian","Zhouchen Lin","Tie-Yan Liu"],"abstract":"High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images. However, typical image downscaling is a non-injective mapping due to the loss of high-frequency information, which leads to the ill-posed problem of the inverse upscaling procedure and poses great challenges for recovering details from the downscaled low-resolution images. Simply upscaling with image super-resolution methods results in unsatisfactory recovering performance. In this work, we propose to solve this problem by modeling the downscaling and upscaling processes from a new perspective, i.e. an invertible bijective transformation, which can largely mitigate the ill-posed nature of image upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process. In this way, upscaling is made tractable by inversely passing a randomly-drawn latent variable with the low-resolution image through the network. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of image upscaling reconstruction from downscaled images.","url_abs":"https://arxiv.org/abs/2005.05650v1","url_pdf":"https://arxiv.org/pdf/2005.05650v1.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":"invertible-image-rescaling","repo_url":"https://github.com/pkuxmq/Invertible-Image-Rescaling","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/LCM1999/VolumeRescaling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/Ash-Lee233/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/JoegameZhou/ms-irn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/Mind23-2/MindCode-101/tree/main/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/andreasfloros/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/jiean001/models_m/tree/main/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/IRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"invertible-image-rescaling","repo_url":"https://github.com/smc-x/ms-irn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-rescaling","task_name":"Image Rescaling"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"irn","method_name":"IRN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-rescaling-on-bsd100-2x","task":"Image Rescaling","dataset":"BSD100-2x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"41.32","SSIM":"0.9876"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-bsd100-4x","task":"Image Rescaling","dataset":"BSD100-4x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"31.64","SSIM":"0.8826"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-2x","task":"Image Rescaling","dataset":"DIV2K val-2x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"44.32","SSIM":"0.9908"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-4x","task":"Image Rescaling","dataset":"DIV2K val-4x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"35.07","SSIM":"0.9318"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q30-2x","task":"Image Rescaling","dataset":"DIV2K val-q30-2x","model":"IRN","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"29.24","SSIM":"0.8051"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q30-4x","task":"Image Rescaling","dataset":"DIV2K val-q30-4x","model":"IRN","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"25.98","SSIM":"0.6867"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q50-2x","task":"Image Rescaling","dataset":"DIV2K val-q50-2x","model":"IRN","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"30.20","SSIM":"0.8342"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q50-4x","task":"Image Rescaling","dataset":"DIV2K val-q50-4x","model":"IRN","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"26.62","SSIM":"0.7096"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q70-2x","task":"Image Rescaling","dataset":"DIV2K val-q70-2x","model":"IRN","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"31.14","SSIM":"0.8604"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q70-4x","task":"Image Rescaling","dataset":"DIV2K val-q70-4x","model":"IRN","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"27.24","SSIM":"0.7328"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q90-2x","task":"Image Rescaling","dataset":"DIV2K val-q90-2x","model":"IRN","rank_in_archive_order":3,"of":3,"metrics":{"PSNR":"32.91","SSIM":"0.9023"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-div2k-val-q90-4x","task":"Image Rescaling","dataset":"DIV2K val-q90-4x","model":"IRN","rank_in_archive_order":3,"of":4,"metrics":{"PSNR":"28.42","SSIM":"0.7777"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set14-2x","task":"Image Rescaling","dataset":"Set14-2x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"40.79","SSIM":"0.9778"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set14-4x","task":"Image Rescaling","dataset":"Set14-4x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"32.67","SSIM":"0.9015"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set5-2x","task":"Image Rescaling","dataset":"Set5-2x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"43.99","SSIM":"0.9871"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-set5-4x","task":"Image Rescaling","dataset":"Set5-4x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"36.19","SSIM":"0.9451"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-urban100-2x","task":"Image Rescaling","dataset":"Urban100-2x","model":"IRN","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"39.92","SSIM":"0.9865"},"uses_additional_data":false},{"leaderboard":"/sota/image-rescaling-on-urban100-4x","task":"Image Rescaling","dataset":"Urban100-4x","model":"IRN","rank_in_archive_order":1,"of":2,"metrics":{"PSNR":"31.41","SSIM":"0.9157"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.05650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05650"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/IRN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-3/tree/main/IRN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ash-Lee233/IRN","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/IRN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiean001/models_m/tree/main/IRN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoegameZhou/ms-irn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-101/tree/main/IRN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/smc-x/ms-irn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andreasfloros/IRN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LCM1999/VolumeRescaling","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pkuxmq/Invertible-Image-Rescaling","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":14},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":14,"ran":1,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9394ff2c25b8a988","entry":"calculate_psnr","repo":"pkuxmq/Invertible-Image-Rescaling","repo_kind":"official","path":"metrics/calculate_PSNR_SSIM.py","file_url":"https://github.com/pkuxmq/Invertible-Image-Rescaling/blob/HEAD/metrics/calculate_PSNR_SSIM.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9394ff2c25b8a988"}},{"code_sha256_prefix":"40c52ad98161c17b","entry":"dict2str","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/options/options.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/options/options.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40c52ad98161c17b"}},{"code_sha256_prefix":"ba721aeacc165234","entry":"ssim","repo":"pkuxmq/Invertible-Image-Rescaling","repo_kind":"official","path":"metrics/calculate_PSNR_SSIM.py","file_url":"https://github.com/pkuxmq/Invertible-Image-Rescaling/blob/HEAD/metrics/calculate_PSNR_SSIM.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba721aeacc165234"}},{"code_sha256_prefix":"5aef99e58703c44a","entry":"calculate_ssim","repo":"pkuxmq/Invertible-Image-Rescaling","repo_kind":"official","path":"metrics/calculate_PSNR_SSIM.py","file_url":"https://github.com/pkuxmq/Invertible-Image-Rescaling/blob/HEAD/metrics/calculate_PSNR_SSIM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5aef99e58703c44a"}},{"code_sha256_prefix":"01aa7bd3d5f55770","entry":"count_parameters","repo":"andreasfloros/IRN","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/andreasfloros/IRN/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01aa7bd3d5f55770"}},{"code_sha256_prefix":"4045b447f74b1b70","entry":"define_IDN","repo":"LCM1999/VolumeRescaling","repo_kind":"listed","path":"codes/models/networks.py","file_url":"https://github.com/LCM1999/VolumeRescaling/blob/HEAD/codes/models/networks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4045b447f74b1b70"}},{"code_sha256_prefix":"f729c1e42588847e","entry":"dict_to_nonedict","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/options/options.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/options/options.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f729c1e42588847e"}},{"code_sha256_prefix":"3516a45279831991","entry":"float_distance","repo":"LCM1999/VolumeRescaling","repo_kind":"listed","path":"codes/models/modules/DistanceField.py","file_url":"https://github.com/LCM1999/VolumeRescaling/blob/HEAD/codes/models/modules/DistanceField.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3516a45279831991"}},{"code_sha256_prefix":"168634e8dabebd81","entry":"linear_warmup_lr","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/optim/warmup_cosine_annealing_lr.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/optim/warmup_cosine_annealing_lr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"168634e8dabebd81"}},{"code_sha256_prefix":"e333b3db3a301339","entry":"linear_warmup_lr","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/optim/warmup_multisteplr.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/optim/warmup_multisteplr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e333b3db3a301339"}},{"code_sha256_prefix":"a6bff4162d391ed8","entry":"lr_steps","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/optim/warmup_multisteplr.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/optim/warmup_multisteplr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6bff4162d391ed8"}},{"code_sha256_prefix":"13d4333fb600dfdc","entry":"make_grid","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/utils/util.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/utils/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13d4333fb600dfdc"}},{"code_sha256_prefix":"df072befe275ec6a","entry":"parse","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/options/options.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/options/options.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"df072befe275ec6a"}},{"code_sha256_prefix":"852a7c9de098c70e","entry":"quantize","repo":"andreasfloros/IRN","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/andreasfloros/IRN/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"852a7c9de098c70e"}},{"code_sha256_prefix":"f64366aa6addd1e3","entry":"rgb2y","repo":"andreasfloros/IRN","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/andreasfloros/IRN/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f64366aa6addd1e3"}},{"code_sha256_prefix":"e12f338ec31cda18","entry":"warmup_cosine_annealing_lr","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/optim/warmup_cosine_annealing_lr.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/optim/warmup_cosine_annealing_lr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e12f338ec31cda18"}},{"code_sha256_prefix":"85f7744dc00ae425","entry":"warmup_step_lr","repo":"JoegameZhou/ms-irn","repo_kind":"listed","path":"src/optim/warmup_multisteplr.py","file_url":"https://github.com/JoegameZhou/ms-irn/blob/HEAD/src/optim/warmup_multisteplr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85f7744dc00ae425"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}