{"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/pitfalls-of-the-gram-loss-for-neural-texture","title":"A Sliced Wasserstein Loss for Neural Texture Synthesis","arxiv_id":"2006.07229","date":"2020-06-12","proceeding":"CVPR 2021 1","authors":["Eric Heitz","Kenneth Vanhoey","Thomas Chambon","Laurent Belcour"],"abstract":"We address the problem of computing a textural loss based on the statistics extracted from the feature activations of a convolutional neural network optimized for object recognition (e.g. VGG-19). The underlying mathematical problem is the measure of the distance between two distributions in feature space. The Gram-matrix loss is the ubiquitous approximation for this problem but it is subject to several shortcomings. Our goal is to promote the Sliced Wasserstein Distance as a replacement for it. It is theoretically proven,practical, simple to implement, and achieves results that are visually superior for texture synthesis by optimization or training generative neural networks.","url_abs":"https://arxiv.org/abs/2006.07229v4","url_pdf":"https://arxiv.org/pdf/2006.07229v4.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":"pitfalls-of-the-gram-loss-for-neural-texture","repo_url":"https://github.com/tchambon/A-Sliced-Wasserstein-Loss-for-Neural-Texture-Synthesis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pitfalls-of-the-gram-loss-for-neural-texture","repo_url":"https://github.com/ryushinn/texsyn_sliceW","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"pitfalls-of-the-gram-loss-for-neural-texture","repo_url":"https://github.com/ryushinn/texture_synthesis_sliced_wasserstein","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[],"methods":[],"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}