Surface Texture Synthesis Research Articles

An Improved SOM Based Surface Texture Synthesis

This paper proposed a new method for surface texture synthesis using improved selforganizing maps as the synthesis logic. The method will first loop map the sample image to the target surface until the surface is full filled, then construct a improved selforganizing maps model, in which use sample image as the input level and the target three-dimensional surface as out put level, to adjust the pixel position in target surface, and the mapping area is controlled in the neighborhood of local extremum by reducing search area of variables. The new algorithm not only speed up the synthesis progress, and also enhances the image quality of target surface texture, and compare with the previous algorithm, it is not necessary for the user’s intervention. Compared with previous results for the proof of our concepts, we have successfully implemented the experimental results and the proposed algorithm.

Surface Texture Synthesis and Mixing Using Differential Colors

In neighborhood-based texture synthesis, adjacent local regions need to satisfy color continuity constraints in order to avoid visible seams. Such continuity constraints seriously restrict the variability of synthesized textures, making it impossible to generate new textures by mixing multiple input textures with very different base colors. In this paper, we propose to relax such restrictions and decompose synthesis into two relatively disjoint stages. In the first stage, an intermediate synthesized texture is generated by only considering the high frequency details during region search and matching. Such a scheme broadens the search space during texture synthesis, but may produce obvious seams due to large discontinuities in low frequency components. In the second stage, instead of performing local feathering along these discontinuities, we perform Laplacian texture reconstruction, which retains the high frequency details but computes new consistent low frequency components to eliminate the seams. It does not only affect texels close to the discontinuities, but also modifies the rest of the texels. Therefore, it can be viewed as a global feature-preserving smoothing step, and is more effective than local feathering. Experiments indicate that our twostage synthesis can produce desirable results for regular texture synthesis as well as texture mixing from multiple sources.

Adaptive Surface Texture Synthesis Using Round‐Shaped Neighbourhoods

Abstract This paper presents a novel surface texture synthesis method, which is capable of producing high‐quality results by performing the synthesis within an effective multi‐resolution scheme using an adaptive texture similarity metric. Compared with related works, our method allows us to directly carry out multi‐resolution synthesis without involving complicated operations such as mesh hierarchy and partitioning on the target surface. Also, the adaptive similarity metric focuses on measuring texture properties at different scales ranging from local to global, allowing for consistency within differently‐sized texture structures. Further, with the introduced round shaped neighbourhoods, we can save considerable amount of computation for the surface texture synthesis over variable texture directions. Experimental results are provided and comparisons are made against other latest works.

RotoTexture: Automated Tools for Texturing Raw Video

We propose a video editing system that allows a user to apply a time-coherent texture to a surface depicted in the raw video from a single uncalibrated camera, including the surface texture mapping of a texture image and the surface texture synthesis from a texture swatch. Our system avoids the construction of a 3D shape model and instead uses the recovered normal field to deform the texture so that it plausibly adheres to the undulations of the depicted surface. The texture mapping method uses the nonlinear least-squares optimization of a spring model to control the behavior of the texture image as it is deformed to match the evolving normal field through the video. The texture synthesis method uses a coarse optical flow to advect clusters of pixels corresponding to patches of similarly oriented surface points. These clusters are organized into a minimum advection tree to account for the dynamic visibility of clusters. We take a rather crude approach to normal recovering and optical flow estimation, yet the results are robust and plausible for nearly diffuse surfaces such as faces and t-shirts.

Fast example-based surface texture synthesis via discrete optimization

We synthesize and animate general texture patterns over arbitrary 3D mesh surfaces. The animation is controlled by flow fields over the target mesh, and the texture can be arbitrary user input as long it satisfies the Markov-Random-Field assumptions. We achieve this by extending the texture optimization framework over 3D mesh surfaces. We propose an efficient discrete solver inspired by k-coherence search, allowing interactive flow texture animation while avoiding the blurry blending problem for the least square solver in previous work. Our technique has potential applications ranging from simulation, visualization, and special effects.

Appearance-space texture synthesis

The traditional approach in texture synthesis is to compare color neighborhoods with those of an exemplar. We show that quality is greatly improved if pointwise colors are replaced by appearance vectors that incorporate nonlocal information such as feature and radiance-transfer data. We perform dimensionality reduction on these vectors prior to synthesis, to create a new appearance-space exemplar. Unlike a texton space, our appearance space is low-dimensional and Euclidean. Synthesis in this information-rich space lets us reduce runtime neighborhood vectors from 5x5 grids to just 4 locations. Building on this unifying framework, we introduce novel techniques for coherent anisometric synthesis, surface texture synthesis directly in an ordinary atlas, and texture advection. Remarkably, we achieve all these functionalities in real-time, or 3 to 4 orders of magnitude faster than prior work.

Uniform texture synthesis and texture mapping using global parameterization

Texture mapping and texture synthesis are two popular methods for the decoration of surfaces with visual detail. Here, an existing challenge is to preserve, or at least balance, two competing metrics: scale and angle. In this paper we present two methods for this, both based on global conformal parameterization. First, we describe a texture synthesis algorithm for surfaces with arbitrary topology. By using the conformal parameterization, the 3D surface texture synthesis problem can be converted to a 2D image synthesis problem, which is more intuitive, easier, and conceptually simpler. While the conformality of the parameterization naturally preserves the angles of the texture, in this paper we provide a multi-scale technique to also maintain a more uniform area scaling factor. A second novel contribution is to employ the global parameterization to simultaneously preserve orthogonality and size in texture mapping. For this, we show that a conformal factor-driven mass-spring method offers a convenient way to trade off these two qualitative metrics. Our algorithms are simple, efficient and automatic, and they are theoretically sound and universal to general surfaces as well.