{"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/image-super-resolution-by-neural-texture","title":"Image Super-Resolution by Neural Texture Transfer","arxiv_id":"1903.00834","date":"2019-03-03","proceeding":"CVPR 2019 6","authors":["Zhifei Zhang","Zhaowen Wang","Zhe Lin","Hairong Qi"],"abstract":"Due to the significant information loss in low-resolution (LR) images, it has\nbecome extremely challenging to further advance the state-of-the-art of single\nimage super-resolution (SISR). Reference-based super-resolution (RefSR), on the\nother hand, has proven to be promising in recovering high-resolution (HR)\ndetails when a reference (Ref) image with similar content as that of the LR\ninput is given. However, the quality of RefSR can degrade severely when Ref is\nless similar. This paper aims to unleash the potential of RefSR by leveraging\nmore texture details from Ref images with stronger robustness even when\nirrelevant Ref images are provided. Inspired by the recent work on image\nstylization, we formulate the RefSR problem as neural texture transfer. We\ndesign an end-to-end deep model which enriches HR details by adaptively\ntransferring the texture from Ref images according to their textural\nsimilarity. Instead of matching content in the raw pixel space as done by\nprevious methods, our key contribution is a multi-level matching conducted in\nthe neural space. This matching scheme facilitates multi-scale neural transfer\nthat allows the model to benefit more from those semantically related Ref\npatches, and gracefully degrade to SISR performance on the least relevant Ref\ninputs. We build a benchmark dataset for the general research of RefSR, which\ncontains Ref images paired with LR inputs with varying levels of similarity.\nBoth quantitative and qualitative evaluations demonstrate the superiority of\nour method over state-of-the-art.","url_abs":"http://arxiv.org/abs/1903.00834v2","url_pdf":"http://arxiv.org/pdf/1903.00834v2.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":"image-super-resolution-by-neural-texture","repo_url":"https://github.com/ZZUTK/SRNTT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"image-super-resolution-by-neural-texture","repo_url":"https://github.com/S-aiueo32/srntt-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-stylization","task_name":"Image Stylization"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"reference-based-super-resolution","task_name":"Reference-based Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-super-resolution-on-cufed5-4x-upscaling","task":"Image Super-Resolution","dataset":"CUFED5 - 4x upscaling","model":"SRNTT-l2","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"26.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-sun80-4x-upscaling","task":"Image Super-Resolution","dataset":"Sun80 - 4x upscaling","model":"SRNTT-l2","rank_in_archive_order":2,"of":2,"metrics":{"PSNR":"28.54"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-urban100-4x","task":"Image Super-Resolution","dataset":"Urban100 - 4x upscaling","model":"SRNTT-l2","rank_in_archive_order":52,"of":65,"metrics":{"PSNR":"25.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.00834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00834"}},"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/S-aiueo32/srntt-pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZZUTK/SRNTT","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"135b3dc835ffe6ad","entry":"get_confirm_token","repo":"S-aiueo32/srntt-pytorch","repo_kind":"listed","path":"download_dataset.py","file_url":"https://github.com/S-aiueo32/srntt-pytorch/blob/HEAD/download_dataset.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":"135b3dc835ffe6ad"}},{"code_sha256_prefix":"5c89da48bb9a642f","entry":"gram_matrix","repo":"S-aiueo32/srntt-pytorch","repo_kind":"listed","path":"losses/texture_loss.py","file_url":"https://github.com/S-aiueo32/srntt-pytorch/blob/HEAD/losses/texture_loss.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":"5c89da48bb9a642f"}},{"code_sha256_prefix":"5257ad8080617933","entry":"insert_bn","repo":"S-aiueo32/srntt-pytorch","repo_kind":"listed","path":"models/vgg.py","file_url":"https://github.com/S-aiueo32/srntt-pytorch/blob/HEAD/models/vgg.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":"5257ad8080617933"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}