{"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/full-resolution-image-compression-with","title":"Full Resolution Image Compression with Recurrent Neural Networks","arxiv_id":"1608.05148","date":"2016-08-18","proceeding":"CVPR 2017 7","authors":["George Toderici","Damien Vincent","Nick Johnston","Sung Jin Hwang","David Minnen","Joel Shor","Michele Covell"],"abstract":"This paper presents a set of full-resolution lossy image compression methods\nbased on neural networks. Each of the architectures we describe can provide\nvariable compression rates during deployment without requiring retraining of\nthe network: each network need only be trained once. All of our architectures\nconsist of a recurrent neural network (RNN)-based encoder and decoder, a\nbinarizer, and a neural network for entropy coding. We compare RNN types (LSTM,\nassociative LSTM) and introduce a new hybrid of GRU and ResNet. We also study\n\"one-shot\" versus additive reconstruction architectures and introduce a new\nscaled-additive framework. We compare to previous work, showing improvements of\n4.3%-8.8% AUC (area under the rate-distortion curve), depending on the\nperceptual metric used. As far as we know, this is the first neural network\narchitecture that is able to outperform JPEG at image compression across most\nbitrates on the rate-distortion curve on the Kodak dataset images, with and\nwithout the aid of entropy coding.","url_abs":"http://arxiv.org/abs/1608.05148v2","url_pdf":"http://arxiv.org/pdf/1608.05148v2.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":"full-resolution-image-compression-with","repo_url":"https://github.com/1zb/pytorch-image-comp-rnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/edmontdants/RNN-LSTM-GRU_Tensorflow-Hybrid-Model-Residual-GRU-ResNet-Toderici2017-CVPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/ika-rwth-aachen/point-cloud-compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/sakurusurya2000/RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"WTFPL"}},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/tensorflow/models/tree/master/research/compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/tensorflow/models/tree/master/research/gan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"full-resolution-image-compression-with","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/d2l/chapter_09_recurrent-modern","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gru","method_name":"GRU"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"masked-convolution","method_name":"Masked Convolution"},{"method_slug":"pixelrnn","method_name":"PixelRNN"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"residual-gru","method_name":"Residual GRU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"residual-gru","name":"Residual GRU","full_name":"Residual GRU"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.05148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.05148"}},"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/sakurusurya2000/RNN","reach":{"status":"ok","spdx":"WTFPL"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1zb/pytorch-image-comp-rnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ika-rwth-aachen/point-cloud-compression","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/compression","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/edmontdants/RNN-LSTM-GRU_Tensorflow-Hybrid-Model-Residual-GRU-ResNet-Toderici2017-CVPR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/d2l/chapter_09_recurrent-modern","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/gan","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"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":"1340f62713f37f16","entry":"load_image_uint16","repo":"ika-rwth-aachen/point-cloud-compression","repo_kind":"listed","path":"range_image_compression/image_utils.py","file_url":"https://github.com/ika-rwth-aachen/point-cloud-compression/blob/HEAD/range_image_compression/image_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":"1340f62713f37f16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}