NIFTY: a Non-Local Image Flow Matching for Texture Synthesis
This work addresses texture synthesis for computer graphics and vision applications, presenting an incremental improvement by integrating modern and classical methods.
The paper tackles exemplar-based texture synthesis by introducing NIFTY, a hybrid framework that combines diffusion models and patch-based techniques, resulting in a method that avoids neural network training and reduces visual artifacts compared to existing approaches.
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