{"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/laplacian-steered-neural-style-transfer","title":"Laplacian-Steered Neural Style Transfer","arxiv_id":"1707.01253","date":"2017-07-05","proceeding":null,"authors":["Shaohua Li","Xinxing Xu","Liqiang Nie","Tat-Seng Chua"],"abstract":"Neural Style Transfer based on Convolutional Neural Networks (CNN) aims to\nsynthesize a new image that retains the high-level structure of a content\nimage, rendered in the low-level texture of a style image. This is achieved by\nconstraining the new image to have high-level CNN features similar to the\ncontent image, and lower-level CNN features similar to the style image. However\nin the traditional optimization objective, low-level features of the content\nimage are absent, and the low-level features of the style image dominate the\nlow-level detail structures of the new image. Hence in the synthesized image,\nmany details of the content image are lost, and a lot of inconsistent and\nunpleasing artifacts appear. As a remedy, we propose to steer image synthesis\nwith a novel loss function: the Laplacian loss. The Laplacian matrix\n(\"Laplacian\" in short), produced by a Laplacian operator, is widely used in\ncomputer vision to detect edges and contours. The Laplacian loss measures the\ndifference of the Laplacians, and correspondingly the difference of the detail\nstructures, between the content image and a new image. It is flexible and\ncompatible with the traditional style transfer constraints. By incorporating\nthe Laplacian loss, we obtain a new optimization objective for neural style\ntransfer named Lapstyle. Minimizing this objective will produce a stylized\nimage that better preserves the detail structures of the content image and\neliminates the artifacts. Experiments show that Lapstyle produces more\nappealing stylized images with less artifacts, without compromising their\n\"stylishness\".","url_abs":"http://arxiv.org/abs/1707.01253v2","url_pdf":"http://arxiv.org/pdf/1707.01253v2.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":"laplacian-steered-neural-style-transfer","repo_url":"https://github.com/askerlee/lapstyle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"laplacian-steered-neural-style-transfer","repo_url":"https://github.com/samwatts98/Fast-Neural-Style-Transfer-with-Laplacian-Loss-TensorFlow-1.13","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"laplacian-steered-neural-style-transfer","repo_url":"https://github.com/xxxNARUTO228xxx/Neural-Style-Transfer-Gatys-LapStyle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.01253"}},"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/askerlee/lapstyle","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xxxNARUTO228xxx/Neural-Style-Transfer-Gatys-LapStyle","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samwatts98/Fast-Neural-Style-Transfer-with-Laplacian-Loss-TensorFlow-1.13","reach":{"status":"unanswered"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"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":1,"samples":[{"code_sha256_prefix":"d25e295e54f4d5a6","entry":"imread","repo":"askerlee/lapstyle","repo_kind":"official","path":"tf-neural-style/neural_style.py","file_url":"https://github.com/askerlee/lapstyle/blob/HEAD/tf-neural-style/neural_style.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d25e295e54f4d5a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}