NITES: A Non-Parametric Interpretable Texture Synthesis Method
A non-parametric interpretable texture synthesis method, called the NITES method, is proposed in this work. Although automatic synthesis of visually pleasant texture can be achieved by deep neural networks nowadays, the associated generation models are mathematically intractable and their training demands higher computational cost. NITES offers a new texture synthesis solution to address these shortcomings. NITES is mathematically transparent and efficient in training and inference. The input is a single exemplary texture image. The NITES method crops out patches from the input and analyzes the statistical properties of these texture patches to obtain their joint spatial-spectral representations. Then, the probabilistic distributions of samples in the joint spatial-spectral spaces are characterized. Finally, numerous texture images that are visually similar to the exemplary texture image can be generated automatically. Experimental results are provided to show the superior quality of generated texture images and efficiency of the proposed NITES method in terms of both training and inference time.
Code (0)
등록된 구현이 없습니다.
Tasks
Texture SynthesisSimilar Papers 제목 키워드 기반
Nonparametric Bayesian Texture Learning and Synthesis
We present a nonparametric Bayesian method for texture learning and synthesis. A texture image is represented by a 2D-Hidden Markov Model (2D-HMM) where the hidden states correspond to the cluster labeling of textons an…
Image SegmentationSemantic SegmentationTexture SynthesisSynthesising Dynamic Textures using Convolutional Neural Networks
Here we present a parametric model for dynamic textures. The model is based on spatiotemporal summary statistics computed from the feature representations of a Convolutional Neural Network (CNN) trained on object recogni…
Object RecognitionCo-occurrence Based Texture Synthesis
As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate. In this work, we turn to co-occurrence statistics, which have lon…
Generative Adversarial NetworkImage GenerationMORPHTexture Classification+1Texture Synthesis Using Shallow Convolutional Networks with Random Filters
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classified as b…
Texture SynthesisNIFTY: a Non-Local Image Flow Matching for Texture Synthesis
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 pat…
Patch Matching