{"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/is-the-deconvolution-layer-the-same-as-a","title":"Is the deconvolution layer the same as a convolutional layer?","arxiv_id":"1609.07009","date":"2016-09-22","proceeding":null,"authors":["Wenzhe Shi","Jose Caballero","Lucas Theis","Ferenc Huszar","Andrew Aitken","Christian Ledig","Zehan Wang"],"abstract":"In this note, we want to focus on aspects related to two questions most\npeople asked us at CVPR about the network we presented. Firstly, What is the\nrelationship between our proposed layer and the deconvolution layer? And\nsecondly, why are convolutions in low-resolution (LR) space a better choice?\nThese are key questions we tried to answer in the paper, but we were not able\nto go into as much depth and clarity as we would have liked in the space\nallowance. To better answer these questions in this note, we first discuss the\nrelationships between the deconvolution layer in the forms of the transposed\nconvolution layer, the sub-pixel convolutional layer and our efficient\nsub-pixel convolutional layer. We will refer to our efficient sub-pixel\nconvolutional layer as a convolutional layer in LR space to distinguish it from\nthe common sub-pixel convolutional layer. We will then show that for a fixed\ncomputational budget and complexity, a network with convolutions exclusively in\nLR space has more representation power at the same speed than a network that\nfirst upsamples the input in high resolution space.","url_abs":"http://arxiv.org/abs/1609.07009v1","url_pdf":"http://arxiv.org/pdf/1609.07009v1.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":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/anujdutt9/ESPCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/atriumlts/subpixel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/sgrvinod/a-pytorch-tutorial-to-super-resolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/tensorlayer/SRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/tetrachrome/subpixel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"is-the-deconvolution-layer-the-same-as-a","repo_url":"https://github.com/zsdonghao/SRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.07009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07009"}},"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/tensorlayer/SRGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/atriumlts/subpixel","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anujdutt9/ESPCN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zsdonghao/SRGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sgrvinod/a-pytorch-tutorial-to-super-resolution","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tetrachrome/subpixel","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"listed":{"samples":10,"ran":0,"repositories":2}},"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":"cd4e6d34bb9ba789","entry":"binary_cross_entropy","repo":"atriumlts/subpixel","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/atriumlts/subpixel/blob/HEAD/ops.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":"cd4e6d34bb9ba789"}},{"code_sha256_prefix":"84054f1f501dc0ba","entry":"calculate_psnr","repo":"anujdutt9/ESPCN","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/anujdutt9/ESPCN/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":"84054f1f501dc0ba"}},{"code_sha256_prefix":"f0cb37d52c4b56e2","entry":"conv2d","repo":"atriumlts/subpixel","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/atriumlts/subpixel/blob/HEAD/ops.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":"f0cb37d52c4b56e2"}},{"code_sha256_prefix":"f62556c1124a15ae","entry":"conv_cond_concat","repo":"atriumlts/subpixel","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/atriumlts/subpixel/blob/HEAD/ops.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":"f62556c1124a15ae"}},{"code_sha256_prefix":"67536e62bea58293","entry":"download","repo":"atriumlts/subpixel","repo_kind":"listed","path":"download.py","file_url":"https://github.com/atriumlts/subpixel/blob/HEAD/download.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":"67536e62bea58293"}},{"code_sha256_prefix":"0fad04de16b2a694","entry":"get_data_loader","repo":"anujdutt9/ESPCN","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/anujdutt9/ESPCN/blob/HEAD/dataloader.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":"0fad04de16b2a694"}},{"code_sha256_prefix":"a270ba2f61b9c333","entry":"get_image","repo":"atriumlts/subpixel","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/atriumlts/subpixel/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":"a270ba2f61b9c333"}},{"code_sha256_prefix":"88f203bb21490547","entry":"imread","repo":"atriumlts/subpixel","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/atriumlts/subpixel/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":"88f203bb21490547"}},{"code_sha256_prefix":"2ec2384ed148df49","entry":"prepare_image","repo":"anujdutt9/ESPCN","repo_kind":"listed","path":"infer.py","file_url":"https://github.com/anujdutt9/ESPCN/blob/HEAD/infer.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":"2ec2384ed148df49"}},{"code_sha256_prefix":"22bcbbee304eaa07","entry":"save_images","repo":"atriumlts/subpixel","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/atriumlts/subpixel/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":"22bcbbee304eaa07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}