A. Zalesny and L. van Gool. A compact model for viewpoint dependent texture synthesis. SMILE 2000.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....into question, in the case of texture synthesis, by the approach of Efros and Leung [6] They demonstrated that superior synthesis results could be obtained using local pixel neighbourhoods directly, without resorting to large scale filter banks. In a related development, Zalesny and Van Gool [18] also eschewed filter banks in favour of a Markov Random Field (MRF) model. Both these works put MRFs firmly back on the map as far as texture synthesis was concerned. Efros and Leung gave a computational method for generating a texture with similar MRF statistics to the original sample, but ....

....of the MRF classifier is superior to the other classifiers. In fact, the result for the 7 x 7 case is bet ter than the best performance achieved for MR8 (97.43 using 2440 textons) Up to now, modelling the full conditional PDF was considered infeasible, and either parametrised Gibbs potentials [8, 18] or at best a combination of marginals [19] were used. The texton representation developed here is different from traditional MRF models which learn potential functions and then use the Hammersley Clifford theorem to calculate the joint probability p(I) 12] We, on the other hand, do not ....

[Article contains additional citation context not shown here]

A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. In Proc. ECCV, LNCS 2018.

....are used for model learning, and classification accuracy is assessed on the 46 images for each texture class in the second (test) set. The materials in the CUReT database are examples of 3D textures and exhibit a marked variation in appearance with changes in viewing and illumination conditions [1, 2, 3, 6, 10]. The difficulty of single image classification is highlighted by figure 4 which illustrates how drastically the appearance of a texture can change with varying imaging conditions. Modelling such textures by a single probability distribution of filter responses [5, 8] may fail in such a situation. ....

A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. volume 2018.

....set are used for model learning, and classication accuracy is assessed on the 46 images for each texture class in the second (test) set. The materials in the CUReT database are examples of 3D textures and exhibit a marked variation in appearance with changes in viewing and illumination conditions [1, 2, 3, 6, 10]. The difculty of single image classication is highlighted by gure 4 which illustrates how drastically the appearance of a texture can change with varying imaging conditions. Modelling such textures by a single probability distribution of lter responses [5, 8] may fail in such a situation. The ....

A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. volume 2018.

....angle. There is a considerable difference in the appearance across images. The need to seriously address 3D effects where the appearance varies considerably with viewpoint and lighting is illustrated in figure 1. The importance of such effects for classification [1, 4, 5] and synthesis [15, 19] has also been noted by other researchers. Our approach to the classification problem is to model a texture as a distribution over textons, and learn the textons and texture models from training images. Classification of a novel image then proceeds by mapping the image to a texton distribution ....

A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. volume

....structure and its difference histogram to the statistical parameter set. 5. Synthesize a new texture using the updated neighborhood structure and statistical parameter set. This texture should have the prescribed statistics of the parameter set for all clique types in the neighborhood structure [20]. 6. Go to step 3. For this texture analysis algorithm, repeated texture synthesis is necessary (step 5) We use the same algorithm as for the synthesis from the final texture model. This algorithm is based on the Gibbs Random Field image representation. It is described in [19] and the ....

....step 3. For this texture analysis algorithm, repeated texture synthesis is necessary (step 5) We use the same algorithm as for the synthesis from the final texture model. This algorithm is based on the Gibbs Random Field image representation. It is described in [19] and the complementary paper [20], where also other aspects of the above modeling procedure are described in more detail. Although we cannot repeat the details here, it is useful to point out a number of features of the synthesis scheme. These also bring out the difference with a number of alternative approaches. The algorithm ....

[Article contains additional citation context not shown here]

Alexey Zalesny and Luc Van Gool, "A Compact Model for Viewpoint Dependent Texture Synthesis", SMILE

No context found.

A. Zalesny and L. van Gool. A compact model for viewpoint dependent texture synthesis. SMILE 2000.

No context found.

A. Zalesny and L. Van Gool. A compact model for viewpoint dependent texture synthesis. Lecture Notes in Computer Science, 2018:124--132, 2001.

No context found.

A. Zalesny and L. van Gool. A compact model for viewpoint dependent texture synthesis. SMILE 2000.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC