用非局部流匹配实现无需训练的高质量纹理合成
NIFTY: a Non-Local Image Flow Matching for Texture Synthesis
- 基于非局部块匹配构建无参数流匹配模型
- 避免传统方法的初始化差和视觉伪影问题
- 适合追求高效、无需训练的纹理生成场景
本文解决基于样本的纹理合成问题。提出NIFTY，一种融合扩散模型与经典块匹配优化思想的混合框架。NIFTY是一种基于非局部块匹配的非参数流匹配模型，无需神经网络训练，同时缓解了传统块方法常见的初始化不佳或视觉伪影等问题。实验结果表明，该方法在代表性对比方法中表现优异。代码已开源：https://github.com/PierrickCh/Nifty.git
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。