High quality solid texture synthesis using position and index histogram matching

Abstract

International audienceThe synthesis quality is one of the most important aspects in solid texture synthesis algorithms. In recent years several methods are proposed to generate high quality solid textures. However, these existing methods often suffer from the synthesis artifacts such as blurring, missing texture structures, introducing aberrant voxel colors, and so on. In this paper, we introduce a novel algorithm for synthesizing high quality solid textures from 2D exemplars. We first analyze the relevant factors for further improvements of the synthesis quality, and then adopt an optimization framework with the k-coherence search and the discrete solver for solid texture synthesis. The texture optimization approach is integrated with two new kinds of histogram matching methods, position and index histogram matching, which effectively cause the global statistics of the synthesized solid textures to match those of the exemplars. Experimental results show that our algorithm outperforms or at least is comparable to the previous solid texture synthesis algorithms in terms of the synthesis quality

Non-parametric synthesis of laminar volumetric textures from a 2D sample

“…Chen and Wang's algorithm [3], proposing a high quality texture synthesis by integrating in the texture optimization process two new kinds of matching histograms.…”

“…To ameliorate these drawbacks, Chen and Wang [3] propose a new modus operandi for texture optimization approaches. Mainly, it consists in using two new kinds of histograms -position and index histograms [3] and in updating the output voxel using the discrete solver as Han et al [7].…”

“…To ameliorate these drawbacks, Chen and Wang [3] propose a new modus operandi for texture optimization approaches. Mainly, it consists in using two new kinds of histograms -position and index histograms [3] and in updating the output voxel using the discrete solver as Han et al [7]. Prior to synthesis, for every pixel in the exemplar, the k best matches are found in the exemplar, idea inspired from the natural texture synthesis algorithm proposed by Ashikmin [8].…”

“…Several authors have proposed different algorithms that intend to better reproduce, in the output texture, the diversity learned in the input sample. Hence, we turn our attention to the improved algorithm proposed by Kopf et al [2] and the particular histogram matching approach of Chen and Wang [3]. In addition, we propose to visit the voxels during synthesis according to the 3D extension of space filling curves.…”

“…The range of applicability of the procedural approaches [6,9,10] remains sparse, leading mostly to algorithms hard to optimize [6,[22][23][24]. In opposition to the global growth procedure involved in the procedural methods, the local methods [1][2][3][4][11][12][13] generate the texture one voxel/patch at a time maintaining the coherence of the local texture with its vicinity. Some of the most underlined synthesis methods based on local optimization are the exemplar-based synthesis algorithms.…”