Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2
We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of broader range of textures, from those with regular structures to completely stochastic ones. To train and evaluate the proposed approach, we construct a comprehensive high-resolution dataset that captures the diversity of natural textures as well as stochastic variations within each perceptually uniform texture. Experimental results demonstrate that the proposed approach yields significantly better quality textures than the state of the art. The ultimate goal of this work is a comprehensive understanding of texture space.
Code (1)
Tasks
DiversityInductive BiasTexture 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 SynthesisBy-Example Synthesis of Vector Textures
We propose a new method for synthesizing an arbitrarily sized novel vector texture given a single raster exemplar. Our method first segments the exemplar to extract the primary textons, and then clusters them based on vi…
Toward a Universal Model for Shape From Texture
We consider the shape from texture problem, where the input is a single image of a curved, textured surface, and the texture and shape are both a priori unknown. We formulate this task as a three-player game between a sh…
modelShape from TextureTexture SynthesisCompositional Neural Textures
Texture plays a vital role in enhancing visual richness in both real photographs and computer-generated imagery. However, the process of editing textures often involves laborious and repetitive manual adjustments of text…
Texture ClassificationSuperpixel based Class-Semantic Texton Occurrences for Natural Roadside Vegetation Segmentation
Vegetation segmentation from roadside data is a field that has received relatively little attention in present studies, but can be of great potentials in a wide range of real-world applications, such as road safety asses…
SegmentationSuperpixels