{"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/real-time-style-transfer-with-strength","title":"Real-Time Style Transfer With Strength Control","arxiv_id":"1904.08643","date":"2019-04-18","proceeding":null,"authors":["Victor Kitov"],"abstract":"Style transfer is a problem of rendering a content image in the style of\nanother style image. A natural and common practical task in applications of\nstyle transfer is to adjust the strength of stylization. Algorithm of Gatys et\nal. (2016) provides this ability by changing the weighting factors of content\nand style losses but is computationally inefficient. Real-time style transfer\nintroduced by Johnson et al. (2016) enables fast stylization of any image by\npassing it through a pre-trained transformer network. Although fast, this\narchitecture is not able to continuously adjust style strength. We propose an\nextension to real-time style transfer that allows direct control of style\nstrength at inference, still requiring only a single transformer network. We\nconduct qualitative and quantitative experiments that demonstrate that the\nproposed method is capable of smooth stylization strength control and removes\ncertain stylization artifacts appearing in the original real-time style\ntransfer method. Comparisons with alternative real-time style transfer\nalgorithms, capable of adjusting stylization strength, show that our method\nreproduces style with more details.","url_abs":"http://arxiv.org/abs/1904.08643v1","url_pdf":"http://arxiv.org/pdf/1904.08643v1.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":"real-time-style-transfer-with-strength","repo_url":"https://github.com/Apogentus/style-transfer-with-strength-control","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}