{"ID":2865329,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22318","arxiv_id":"2509.22318","title":"NIFTY: a Non-Local Image Flow Matching for Texture Synthesis","abstract":"This paper addresses the problem of exemplar-based texture synthesis. We introduce NIFTY, a hybrid framework that combines recent insights on diffusion models trained with convolutional neural networks, and classical patch-based texture optimization techniques. NIFTY is a non-parametric flow-matching model built on non-local patch matching, which avoids the need for neural network training while alleviating common shortcomings of patch-based methods, such as poor initialization or visual artifacts. Experimental results demonstrate the effectiveness of the proposed approach compared to representative methods from the literature. Code is available at https://github.com/PierrickCh/Nifty.git","short_abstract":"This paper addresses the problem of exemplar-based texture synthesis. We introduce NIFTY, a hybrid framework that combines recent insights on diffusion models trained with convolutional neural networks, and classical patch-based texture optimization techniques. NIFTY is a non-parametric flow-matching model built on non...","url_abs":"https://arxiv.org/abs/2509.22318","url_pdf":"https://arxiv.org/pdf/2509.22318v1","authors":"[\"Pierrick Chatillon\",\"Julien Rabin\",\"David Tschumperlé\"]","published":"2025-09-26T13:19:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":609262,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2865329,"paper_url":"https://arxiv.org/abs/2509.22318","paper_title":"NIFTY: a Non-Local Image Flow Matching for Texture Synthesis","repo_url":"https://github.com/PierrickCh/Nifty.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}