An Automatic Texture Generation Algorithm for 3D Shapes Based on cGAN
1
Citation
13
Reference
10
Related Paper
Citation Trend
Abstract:
Abstract Texturing 3D shapes is of great importance in computer graphics with applications ranging from game design to augmented reality. However, the processes of texture generation are usually tedious, time-consuming and labor-intensive. In this paper, we propose an automatic texture generation algorithm for 3D shapes based on conditional Generative Adversarial Networks (cGAN). The core of our algorithm includes sampling the model outline and building a cGAN in order to generate model textures automatically. In particular, we propose a novel edge detection method using 3D model information which can accurately find the outline of the model to improve the quality of the generated texture. Due to the adaptability of the algorithm, our approach is suitable for texture generation for most 3D models. Experimental results show the efficiency of our algorithm which can easily generate high quality model textures.Keywords:
Texture (cosmology)
Adaptability
Texture Synthesis
Abstract Solid (30) texturing is commonly used in computer graphics for producing more realistic images. It is often more attractive than the conventional 20 texture mapping but remains more complex on some points. Its major difficulty concerns the generation of 30 texture in a general and efficient way. The well‐known traditional procedural methods use generally a simplified mathematical model of a natural texture. No reliable way for the choice of the mathematical model parameters, which characterise directly the produced 30 texture, is given. Therefore, 30 texture generation becomes a more or less experimental process with these methods. Our recently published methodfor an automatic 30 texture generation avoids this problem by the use of the spectral analysis of one 2D model texture. The resulting 30 texture is of good quality but one open problem remains: the aspect of the produced texture cannot be fully controlled over the entire 30 space by only one 20 spectral analysis. This may be considered as a serious limitation for some kinds of textures representing important variations in any direction. In this paper we present a new and more powerful analytical approach for an automatic 30 texture generation. Contrarily to our previous method, this new approach is not exclusively based on the spectral analysis of only one 20 model. It uses two or three 2D models corresponding to different slices of a 30 texture block, so, the aspect of the produced 3D texture can be controlled more efficiently over the entire 30 space. In addition, a more efficient 30 texture antialiasing, well adapted to this new method is presented.
Texture (cosmology)
Texture compression
Texture Synthesis
Texture filtering
Bidirectional texture function
Texture atlas
Projective texture mapping
Displacement mapping
Cite
Citations (46)
Texture (cosmology)
Texture Synthesis
Texture filtering
Texture compression
Texel
Cite
Citations (8)
Texture synthesis has proven successful at imitating a wide variety of textures. Adding additional constraints (in the form of a low-resolution version of the texture to be synthesized) makes it possible to use texture synthesis methods for texture superresolution.
Texture (cosmology)
Texture Synthesis
Texture compression
Texture filtering
Bidirectional texture function
Cite
Citations (0)
Extending the real-time texture synthesis by patch-based sampling and applying it to constrained texture synthesis, we repaired the blemish. By means of different types of texture segment to find matching and the texture patch which can change in size, we repaired the boundary of the blemish, making no obvious sense of fringe in the boundary of the repaired picture.
Texture Synthesis
Texture (cosmology)
Texture filtering
Bidirectional texture function
Texture compression
Projective texture mapping
Cite
Citations (1)
We introduce procedural texture particles, a new texture model at mid-way between procedural textures and example-based texture synthesis. As for example-based texture synthesis, we use an input example to produce similar looking textures. But instead of creating texture images (pixel arrays), our textures are defined in the form of procedural distributions of interchangeable visual elements called particles. As for classical example-based synthesis, our method guarantees a certain visual resemblance with the example, but obtained textures are compact and defined on the entire infinite 2D plane.
Texture (cosmology)
Texture filtering
Texture Synthesis
Projective texture mapping
Procedural modeling
Texture compression
Texture atlas
Bidirectional texture function
Cite
Citations (1)
Seamless montage for texturing 3D models is very important in 3D video games and computer animations. The goal is to generate an arbitrarily large texture from a small sample image while both the sample texture and the result texture must be perceived by human observers to be the same and there is no obvious seam. This is slightly different from texture synthesis whose main principle is that the result texture must be non-periodical. Since there exist substantial periodical textures in real world, this paper presents a method for seamless montage without seams to form periodical textures. First we apply a quilting algorithm together with Wang Tiles to design the tile for montage, and we make comparison between them in terms of practical maneuverability. Then we employ the tile designed through Wang Tiles for seamless montage to generate a large texture with an arbitrary size. We also consider the montage of 3D surface textures under various illumination directions.
Texture (cosmology)
Texture Synthesis
Texture atlas
Texture filtering
Sample (material)
Quilting
Cite
Citations (2)
Texture Mapping plays a very important role in Computer Graphics. Texture Synthesis is one of the main methods to obtain textures, it makes use of sample textures to generate new textures. Texture Transfer is based on Texture Synthesis, it renders objects with textures taken from different objects. Currently, most of Texture Synthesis and Transfer methods use a single sample texture. A method for Texture Synthesis adn Transfer from multi samples was presented. For texture synthesis, the L-shaped neighborhood seaching approach was used. Users specify the proportion of each sample, the number of seed points, and these seed points are scattered randomly according to their samples in horizontal and vertical direction synchronously to synthesize textures. The synthesized textures are very good. For texture transfer, the luminance of the target image and the sample textures are analyzed. This procedure is from coarse to fine, and can produce a visually pleasing result.
Texture filtering
Texture (cosmology)
Texture Synthesis
Texture atlas
Texture compression
Projective texture mapping
Sample (material)
Bidirectional texture function
Cite
Citations (0)
Texture (cosmology)
Texture Synthesis
Texture filtering
Texture compression
Texel
Cite
Citations (72)
The traditional examplar-based texture synthesis algorithm is lack of adaptability since the Size Of Patches(SOP)needs to be defined artificially in advance or adjusted according to the completion effect.In order to solve this problem,a method for adaptively selecting the SOP is proposed.The images are pre-processed with the image decomposition technique.The image texture features are extracted.The SOP is automatically selected according to the relationship with the extracted texture features.Simulation results show that the suitable effect of texture synthesis can be obtained with the SOP selected by the proposed method.
Texture (cosmology)
Texture Synthesis
Adaptability
Texture filtering
Cite
Citations (3)