{"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/accelerating-the-super-resolution","title":"Accelerating the Super-Resolution Convolutional Neural Network","arxiv_id":"1608.00367","date":"2016-08-01","proceeding":null,"authors":["Chao Dong","Chen Change Loy","Xiaoou Tang"],"abstract":"As a successful deep model applied in image super-resolution (SR), the\nSuper-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior\nperformance to the previous hand-crafted models either in speed and restoration\nquality. However, the high computational cost still hinders it from practical\nusage that demands real-time performance (24 fps). In this paper, we aim at\naccelerating the current SRCNN, and propose a compact hourglass-shape CNN\nstructure for faster and better SR. We re-design the SRCNN structure mainly in\nthree aspects. First, we introduce a deconvolution layer at the end of the\nnetwork, then the mapping is learned directly from the original low-resolution\nimage (without interpolation) to the high-resolution one. Second, we\nreformulate the mapping layer by shrinking the input feature dimension before\nmapping and expanding back afterwards. Third, we adopt smaller filter sizes but\nmore mapping layers. The proposed model achieves a speed up of more than 40\ntimes with even superior restoration quality. Further, we present the parameter\nsettings that can achieve real-time performance on a generic CPU while still\nmaintaining good performance. A corresponding transfer strategy is also\nproposed for fast training and testing across different upscaling factors.","url_abs":"http://arxiv.org/abs/1608.00367v1","url_pdf":"http://arxiv.org/pdf/1608.00367v1.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":"accelerating-the-super-resolution","repo_url":"https://github.com/Araxeus/PNG-Upscale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/GatorSense/SRrootimaging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/Lornatang/FSRCNN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/MohammedAlkhrashi/4D-Dream","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/MohammedAlkhrashi/TMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/Nhat-Thanh/FSRCNN-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/Nhat-Thanh/FSRCNN-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/NicoCeresa/FSRCNN-2016","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/OlgaChernytska/Super-Resolution-with-FSRCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/Zorrat/Image-Denoiser-Supersampling-and-Editor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/amiq-consulting/image-upscaling-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/poikilos/pyrotocanvas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/xanderex-sid/FSRCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/yjn870/FSRCNN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"accelerating-the-super-resolution","repo_url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/Super-Resolution-for-Root-Imaging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[{"slug":"general-100","name":"General-100","full_name":"General-100"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-bsd100-2x-upscaling","task":"Image Super-Resolution","dataset":"BSD100 - 2x upscaling","model":"FSRCNN [[Dong et al.2016]]","rank_in_archive_order":30,"of":30,"metrics":{"PSNR":"31.53"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-ffhq-1024-x-1024-4x","task":"Image Super-Resolution","dataset":"FFHQ 1024 x 1024 - 4x upscaling","model":"FSRCNN","rank_in_archive_order":6,"of":9,"metrics":{"FID":"23.97","MS-SSIM":"0.951","PSNR":"24.71","SSIM":"0.804"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-ffhq-256-x-256-4x","task":"Image Super-Resolution","dataset":"FFHQ 256 x 256 - 4x upscaling","model":"FSRCNN","rank_in_archive_order":6,"of":11,"metrics":{"FID":"139.78","MS-SSIM":"0.930","PSNR":"22.45","SSIM":"0.709"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-manga109-4x","task":"Image Super-Resolution","dataset":"Manga109 - 4x upscaling","model":"FSRCNN","rank_in_archive_order":44,"of":50,"metrics":{"PSNR":"27.90","SSIM":"0.8610"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.00367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.00367"}},"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/MohammedAlkhrashi/TMA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nhat-Thanh/FSRCNN-Pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yjn870/FSRCNN-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Zorrat/Image-Denoiser-Supersampling-and-Editor","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/poikilos/pyrotocanvas","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-11/tree/main/Super-Resolution-for-Root-Imaging","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MohammedAlkhrashi/4D-Dream","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Araxeus/PNG-Upscale","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amiq-consulting/image-upscaling-CNN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lornatang/FSRCNN-PyTorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xanderex-sid/FSRCNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GatorSense/SRrootimaging","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nhat-Thanh/FSRCNN-TF","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OlgaChernytska/Super-Resolution-with-FSRCNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NicoCeresa/FSRCNN-2016","reach":{"status":"ok"}}],"summary":{"unverified":15},"by_repo_kind":{"listed":{"samples":15,"ran":0,"repositories":4}},"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":"dd97234bcfdf3615","entry":"FSRCNN","repo":"MaxHolmberg96/Fast-super-resolution-by-CNN","repo_kind":"listed","path":"fsrcnn.py","file_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN/blob/HEAD/fsrcnn.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":"dd97234bcfdf3615"}},{"code_sha256_prefix":"9380592364aafe4f","entry":"FSRCNN","repo":"Nhat-Thanh/FSRCNN-TF","repo_kind":"listed","path":"neuralnet.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-TF/blob/HEAD/neuralnet.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":"9380592364aafe4f"}},{"code_sha256_prefix":"7dfb710bae9177e3","entry":"convert_rgb_to_y","repo":"MaxHolmberg96/Fast-super-resolution-by-CNN","repo_kind":"listed","path":"data.py","file_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN/blob/HEAD/data.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":"7dfb710bae9177e3"}},{"code_sha256_prefix":"e0dcb85fc7cb24b0","entry":"convert_rgb_to_ycbcr","repo":"MaxHolmberg96/Fast-super-resolution-by-CNN","repo_kind":"listed","path":"data.py","file_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN/blob/HEAD/data.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":"e0dcb85fc7cb24b0"}},{"code_sha256_prefix":"3e396b602fde8231","entry":"convert_ycbcr_to_rgb","repo":"MaxHolmberg96/Fast-super-resolution-by-CNN","repo_kind":"listed","path":"data.py","file_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN/blob/HEAD/data.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":"3e396b602fde8231"}},{"code_sha256_prefix":"0d462506dbb0db2d","entry":"cubic","repo":"Lornatang/FSRCNN-PyTorch","repo_kind":"listed","path":"imgproc.py","file_url":"https://github.com/Lornatang/FSRCNN-PyTorch/blob/HEAD/imgproc.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":"0d462506dbb0db2d"}},{"code_sha256_prefix":"4579f4a0e343f30e","entry":"image2tensor","repo":"Lornatang/FSRCNN-PyTorch","repo_kind":"listed","path":"imgproc.py","file_url":"https://github.com/Lornatang/FSRCNN-PyTorch/blob/HEAD/imgproc.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":"4579f4a0e343f30e"}},{"code_sha256_prefix":"df6069cdd75250cc","entry":"psnr","repo":"MaxHolmberg96/Fast-super-resolution-by-CNN","repo_kind":"listed","path":"fsrcnn.py","file_url":"https://github.com/MaxHolmberg96/Fast-super-resolution-by-CNN/blob/HEAD/fsrcnn.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":"df6069cdd75250cc"}},{"code_sha256_prefix":"4d448d32e15f04c9","entry":"read_image","repo":"Nhat-Thanh/FSRCNN-Pytorch","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-Pytorch/blob/HEAD/utils/common.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":"4d448d32e15f04c9"}},{"code_sha256_prefix":"05f12c47fb9b8978","entry":"read_image","repo":"Nhat-Thanh/FSRCNN-TF","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-TF/blob/HEAD/utils/common.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":"05f12c47fb9b8978"}},{"code_sha256_prefix":"d8058eded6a9e999","entry":"rgb2ycbcr","repo":"Nhat-Thanh/FSRCNN-Pytorch","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-Pytorch/blob/HEAD/utils/common.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":"d8058eded6a9e999"}},{"code_sha256_prefix":"3760ee509acdf19f","entry":"rgb2ycbcr","repo":"Nhat-Thanh/FSRCNN-TF","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-TF/blob/HEAD/utils/common.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":"3760ee509acdf19f"}},{"code_sha256_prefix":"bc562954fab9c9fb","entry":"tensor2image","repo":"Lornatang/FSRCNN-PyTorch","repo_kind":"listed","path":"imgproc.py","file_url":"https://github.com/Lornatang/FSRCNN-PyTorch/blob/HEAD/imgproc.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":"bc562954fab9c9fb"}},{"code_sha256_prefix":"ef42ea280e97a9f8","entry":"ycbcr2rgb","repo":"Nhat-Thanh/FSRCNN-Pytorch","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-Pytorch/blob/HEAD/utils/common.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":"ef42ea280e97a9f8"}},{"code_sha256_prefix":"3b0edbcfb724a432","entry":"ycbcr2rgb","repo":"Nhat-Thanh/FSRCNN-TF","repo_kind":"listed","path":"utils/common.py","file_url":"https://github.com/Nhat-Thanh/FSRCNN-TF/blob/HEAD/utils/common.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":"3b0edbcfb724a432"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}