Separation Surfaces in the Spectral TV Domain for Texture Decomposition

TL;DR

This paper introduces a novel spectral TV-based method for texture decomposition using separation surfaces that adaptively encode local texture scales, enabling effective separation and enhancement of textures with varying patterns.

Contribution

It proposes a new separation surface concept in the spectral TV domain for adaptive texture decomposition, improving handling of textures with spatially varying characteristics.

Findings

Effective separation of textures with varying pattern sizes and contrasts

Adaptive scale-range definition via spectral surface fitting

Natural and visually convincing texture enhancement and attenuation

Abstract

In this paper we introduce a novel notion of separation surfaces for image decomposition. A surface is embedded in the spectral total-variation (TV) three dimensional domain and encodes a spatially-varying separation scale. The method allows good separation of textures with gradually varying pattern-size, pattern-contrast or illumination. The recently proposed total variation spectral framework is used to decompose the image into a continuum of textural scales. A desired texture, within a scale range, is found by fitting a surface to the local maximal responses in the spectral domain. A band above and below the surface, referred to as the \textit{Texture Stratum}, defines for each pixel the adaptive scale-range of the texture. Based on the decomposition an application is proposed which can attenuate or enhance textures in the image in a very natural and visually convincing manner.