Refining structural texture synthesis approach

Bartakke, Prashant; Vaidya, Shachi; Sutaone, M. S.

doi:10.1049/iet-ipr.2010.0096

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bartakke et al . [14] proposed the refinement of the structural approach for texture synthesis characterised by repeating the texel under certain placement rules. Despite successful generalisation and reproduction of semi‐periodic texture components as structure, illumination, and variability, the method could not successfully synthesise weakly‐homogeneous textures.…”

Section: Texture Synthesismentioning

confidence: 99%

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Jakab

Hudec

Benešová

2020

IET Computer Vision

View full text Add to dashboard Cite

Multiple research studies have recently demonstrated deep networks can generate realistic‐looking textures and stylised images from a single texture example. However, they suffer from some drawbacks. Generative adversarial networks are in general difficult to train. Multiple feature variations, encoded in their latent representation, require a priori information to generate images with specific features. The auto‐encoders are prone to generate a blurry output. One of the main reasons is the inability to parameterise complex distributions. The authors present a novel texture generative model architecture extending the variational auto‐encoder approach. It gradually increases the accuracy of details in the reconstructed images. Thanks to the proposed architecture, the model is able to learn a higher level of details resulting from the partial disentanglement of latent variables. The generative model is also capable of synthesising complex real‐world textures. The model consists of multiple separate latent layers responsible for learning the gradual levels of texture details. Separate training of latent representations increases the stability of the learning process and provides partial disentanglement of latent variables. The experiments with proposed architecture demonstrate the potential of variational auto‐encoders in the domain of texture synthesis and also tend to yield sharper reconstruction as well as synthesised texture images.

show abstract

Section: Texture Synthesismentioning

confidence: 99%

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Jakab

Hudec

Benešová

2020

IET Computer Vision

View full text Add to dashboard Cite

show abstract

Color human slice segmentation based on texture information

Qian

Zhou

Huang

2012

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery

View full text Add to dashboard Cite

Hybrid MPI-OpenMP Parallelization of Image Reconstruction

Liu¹

2013

JSW

View full text Add to dashboard Cite

Perceptual coding should take full advantage of the results from human visual system (HVS) studies. In this paper, we exploit an image reconstruction algorithm, which can simply and reliably represent images using regional shape and texture information and effectually eliminate perceptual redundancy. But real-time application of the algorithm is limited due to its inherent complex and intensive computation. Therefore, we implement image reconstruction with a hybrid message passing interface (MPI) and OpenMP approach on the basis of a standard MPI implementation. Experimental results confirm our image reconstruction algorithm can get optimal restoration results. Compared with JPEG and JPEG2000 compression, this algorithm can not only get more coding gain but remain most information people care. Our hybrid MPI-OpenMP approach can significantly improve time performance of image reconstruction algorithm

show abstract

Refining structural texture synthesis approach

Cited by 3 publications

References 9 publications

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Partial disentanglement of hierarchical variational auto‐encoder for texture synthesis

Color human slice segmentation based on texture information

Hybrid MPI-OpenMP Parallelization of Image Reconstruction

Contact Info

Product

Resources

About