Fast example-based surface texture synthesis via discrete optimization

Han, Jianwei; Zhou, Kun; Wei, Li-Yi; Gong, Minmin; Bao, Hujun; Zhang, Xin Ming; Guo, Baining

doi:10.1007/s00371-006-0078-3

Cited by 72 publications

(67 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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].…”

Section: Overview Of Chen and Wang's Algorithmmentioning

confidence: 99%

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

Urs¹,

Costa²,

Leyssale³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

The goal of this paper is to evaluate non-parametric algorithms that achieve 3D texture synthesis from a single 2D sample. The algorithms under study are variants of the algorithm proposed by Wei and Levoy [1]. 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. We investigate the algorithms capability to reproduce anisotropic textures. In particular we are interested in laminar textures, i.e. textures made of anisotropic sheets stacked along a given direction. Examples of such textures are snapshots of dense carbons observed by high resolution transmission electronic microscopy (HRTEM). Beyond the traditional subjective evaluation of the synthesized textures, we propose a genuine quantitative benchmark for the analysis of the synthesized textures which consists in comparing input and output gray level statistics and patterns morphology.

show abstract

Section: Overview Of Chen and Wang's Algorithmmentioning

confidence: 99%

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

Urs¹,

Costa²,

Leyssale³

et al. 2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…In particular, it has been found for colors, local coherence is very important and occasional high frequency discontinuities are more tolerable than a texture that is entirely continuous but subject to blur or noise; see discussions in coherence synthesis [Ashikhmin 2001;Tong et al 2002;Han et al 2006] and patch-based synthesis [Liang et al 2001;Efros and Freeman 2001]. However, for motion vectors, we have found the opposite holds true: low frequency noise or blur is usually better than high frequency discontinuity.…”

Section: Motion Detail Synthesis -Same Dimensionmentioning

confidence: 62%

“…However, for motion vectors, we have found the opposite holds true: low frequency noise or blur is usually better than high frequency discontinuity. Thus, in our current implementation, we prefer the original least-squares based texture optimization algorithm [Kwatra et al 2005] rather than the k-coherence enhanced version [Han et al 2006] for quality reasons. However, for speed reasons, we have also developed a version of our algorithm based on k-coherence.…”

Section: Motion Detail Synthesis -Same Dimensionmentioning

confidence: 99%

Motion field texture synthesis

Ma¹,

Wei²,

Guo³

et al. 2009

ACM SIGGRAPH Asia 2009 Papers

Self Cite

View full text Add to dashboard Cite

original motion exemplar synthesized detail motion combined motion field original density field final density fieldFigure 1: Motion field texture synthesis. Given a low-resolution motion field and an input exemplar, we synthesize a high-resolution detailed motion field that resembles the exemplar while follows the local orientation of the low-resolution field. This synthesized detail motion field is then combined with the original low-res motion field to produce the final motion. Our method can produce non-physics-based artistic effects such as fluids with heart-shaped motions. AbstractA variety of animation effects such as herds and fluids contain detailed motion fields characterized by repetitive structures. Such detailed motion fields are often visually important, but tedious to specify manually or expensive to simulate computationally. Due to the repetitive nature, some of these motion fields (e.g. turbulence in fluids) could be synthesized by procedural texturing, but procedural texturing is known for its limited generality.We apply example-based texture synthesis for motion fields. Our technique is general and can take on a variety of user inputs, including captured data, manual art, and physical/procedural simulation. This data-driven approach enables artistic effects that are difficult to achieve via previous methods, such as heart shaped swirls in fluid animation. Due to the use of texture synthesis, our method is able to populate a large output field from a small input exemplar, imposing minimum user workload. Our algorithm also allows the synthesis of output motion fields not only with the same dimension as the input (e.g. 2D to 2D) but also of higher dimension, such as 3D volumetric outputs from 2D planar inputs. This cross-dimension capability supports a convenient usage scenario, i.e. the user could simply supply 2D images and our method produces a 3D motion field with similar characteristics. The motion fields produced by our method are generic, and could be combined with a variety of large-scale low-resolution motions that are easy to specify either manually or computationally but lack the repetitive structures to be characterized as textures. We apply our technique to a variety of animation phenomena, including smoke, liquid, and group motion.

show abstract

“…Connections with previous work Problem (1) is a generic framework for texture synthesis and it is closely related to several approaches from the literature such as [13,17] inspired by the seminal work of [19]. For instance, Kwatra et al [19] use the power r = 0.8 with an Euclidean norm weighted with a Gaussian falloff, and the assignment σ is not constrained to be a permutation, which results in a nearest neighbor matching.…”

Section: Linear Patch Assignment Modelmentioning

confidence: 96%

“…Their success is however not guaranteed: when the input image contains constant or blurry regions, these can be indeed enlarged during the synthesis, creating "garbage regions" [8,1,23]. A more principled approach consists in synthesizing the output texture through the minimization of a patch-based dissimilarity texture energy [19,13]. These methods are able to obtain high quality results for both stochastic and structured textures.…”

Section: Introductionmentioning

confidence: 99%

Optimal Patch Assignment for Statistically Constrained Texture Synthesis

Gutiérrez

Rabin

Galerne

et al. 2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This article introduces a new model for patch-based texture synthesis that controls the distribution of patches in the synthesized texture. The proposed approach relies on an optimal assignment of patches over decimated pixel grids. This assignment problem formulates the synthesis as the minimization of a discrepancy measure between input's and output's patches through their optimal permutation. The resulting nonconvex optimization problem is addressed with an iterative algorithm alternating between a patch assignment step and a patch aggregation step. We show that this model statistically constrains the output texture content, while inheriting the structure-preserving property of patch-based methods. We also propose a relaxed patch assignment extension that increases the robustness to non-stationnary textures.

show abstract

Fast example-based surface texture synthesis via discrete optimization

Cited by 72 publications

References 22 publications

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

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

Motion field texture synthesis

Optimal Patch Assignment for Statistically Constrained Texture Synthesis

Contact Info

Product

Resources

About