Composite Texture Synthesis

Zalesny, Alexey; Ferrari, Vittorio; Caenen, Geert; Gool, Luc Van

doi:10.1007/s11263-005-4640-7

Cited by 20 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zalesny et al [28] propose a hierarchical approach to texture synthesis that considers textures to be composites of simple sub-textures. Han et al [8] use a few low-resolution exemplars as inputs to produce inhomogeneous textures that span large or infinite ranges of scale.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Feature-aware natural texture synthesis

Dong

Kong

et al. 2014

Vis Comput

View full text Add to dashboard Cite

This article presents a framework for natural texture synthesis and processing. This framework is motivated by the observation that given examples captured in natural scene, texture synthesis addresses a critical problem, namely, that synthesis quality can be affected adversely if the texture elements in an example display spatially varied patterns, such as perspective distortion, the composition of different subtextures, and variations in global color pattern as a result of complex illumination. This issue is common in natural textures and is a fundamental challenge for previously developed methods. Thus, we address it from a feature point of view and propose a feature-aware approach to synthesize natural textures. The synthesis process is guided by a feature map that represents the visual characteristics of the input texture. Moreover, we present a novel adaptive initialization algorithm that can effectively avoid the repeat and verbatim copying artifacts. Our approach improves texture synthesis Electronic supplementary material The online version of this article (in many images that cannot be handled effectively with traditional technologies.

show abstract

Section: Related Workmentioning

confidence: 99%

“…1c). Moreover, the example may involve multiple sub-textures of different materials (referred as composite texture [28], e.g., Fig. 2a).…”

Section: Introductionmentioning

confidence: 99%

Feature-aware natural texture synthesis

Dong

Kong

et al. 2014

Vis Comput

View full text Add to dashboard Cite

show abstract

“…On the other hand, their algorithm requires (1) an expensive segmentation step, and (2) a hard decision about what constitutes a boundary between two textures. Zalesny et al (2002), suggested an algorithm for the parallel synthesis of composite textures. They devise a special purpose solution for synthesizing the interface between two "knitted" textures.…”

Section: Filling-in In a Decomposition Spacementioning

confidence: 99%

A review of wave-net identical learning & filling-in in a decomposition space of (JPG-JPEG) sampled images

et al. 2010

View full text Add to dashboard Cite

Continuous flow to send images via encrypted wireless channels may reduce the efficiency of transmission. This is due to the damage or loss of the numerous macro-blocks from these images. Therefore, it is difficult to rebuild these patches from the point of reception. Many algorithms have been proposed in the past decade, particularly error concealment (EC) algorithms. In this paper, we focus on the algorithms that have high efficiency to fill-in the corrupted patches. On the other hand, we also present a new way of detecting the horizontal and vertical gradients especially, in the un-smooth patches. This improves the edge detector filter. Ultimately, a novel scheme for vertical and horizontal interpolation between the corrupted pixels and the non-corrupted adjacent pixels is achieved by improving the efficiency of filling-in. We used a new technique known as the wave-net model. This model combines the wavelet with the neural network classifier (NNC). The neural network was trained in advance to reduce the error extent for the pixels that may occur in the error. The experimental results were convincing and close to the desired. The proposed method is able to enhance image quality in term of both visual perception and the blurriness effects (BE).

show abstract

“…Of particular interest are exemplar-based techniques which cheaply and effectively generate new texture by sampling and copying colour values from the source [1,9,10,11,15]. As effective as these techniques are in replicating consistent texture, they have difficulty filling holes in photographs of real-world scenes, which often consist of linear structures and composite textures -multiple textures interacting spatially [23]. The main problem is that boundaries between image regions are a complex product of mutual influences between different textures.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, Zalesny et al [23] describe an interesting algorithm for the parallel synthesis of composite textures. They devise a special-purpose solution for the interface between two textures.…”

Section: Introductionmentioning

confidence: 99%

Object removal by exemplar-based inpainting

Criminisi

Pérez

Toyama

2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.

659

554

View full text Add to dashboard Cite

A new algorithm is proposed for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way.In the past, this problem has been addressed by two classes of algorithms: (i) "texture synthesis" algorithms for generating large image regions from sample textures, and (ii) "inpainting" techniques for filling in small image gaps. The former work well for "textures" -repeating twodimensional patterns with some stochasticity; the latter focus on linear "structures" which can be thought of as onedimensional patterns, such as lines and object contours.This paper presents a novel and efficient algorithm that combines the advantages of these two approaches. We first note that exemplar-based texture synthesis contains the essential process required to replicate both texture and structure; the success of structure propagation, however, is highly dependent on the order in which the filling proceeds. We propose a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting. The actual colour values are computed using exemplar-based synthesis. Computational efficiency is achieved by a blockbased sampling process.A number of examples on real and synthetic images demonstrate the effectiveness of our algorithm in removing large occluding objects as well as thin scratches. Robustness with respect to the shape of the manually selected target region is also demonstrated. Our results compare favorably to those obtained by existing techniques.

show abstract

Composite Texture Synthesis

Cited by 20 publications

References 15 publications

Feature-aware natural texture synthesis

Feature-aware natural texture synthesis

A review of wave-net identical learning & filling-in in a decomposition space of (JPG-JPEG) sampled images

Object removal by exemplar-based inpainting

Contact Info

Product

Resources

About