Due to the lack of enough generalization in the statespace, common methods in Reinforcement Learning (RL) suffer from slow learning speed especially in the early learning trials. This paper introduces a model-based method in discrete statespaces for increasing the learning speed in terms of required experience (but not required computational time) by exploiting generalization in the experiences...

Morphological antialiasing is a post-processing approach which does note require additional samples computation. This algorithm acts as a non-linear filter, ill-suited to massively parallel hardware architectures. We redesigned the initial method using multiple passes with, in particular, a new approach to line length computation. We also introduce in the method the notion of topological recons...

1 LO, T.K : 'Miniature aperture-coupled microstrip antenna of very high permittivity', Electron. Lett., 1997, 33, pp. 9-10 2 PINHAS, s., and SHTRIKMAN, s.: 'Comparison between computed and measured bandwidth of quarter-wave microstrip radiators', IEEE Trans., 1988, AP-36, (ll), pp. 1615-1616 3 WATERHOUSE, R.B : 'Small microstrip patch antenna', Electron. Lett., 1995, 31, pp. 604605 4 LUK. K.M.,...

A new approach to improve image quality in partially parallel 3D MRI is presented. Aliasing artifacts are manipulated by modifications of the gradient tables in the 3D phase encoding direction in order to achieve improved conditions for the final image reconstruction procedure. In contrast to conventional 3D parallel imaging methods, like 2D SENSE [1], superimposed partitions with essentially i...

We present a method for frame coherent texturing and hatching of 3D models with a discrete set of colors. Our technique is inspired by various artistic styles that use a limited set of colors to convey surface shape and texture. In previous research discrete color shading was produced by modifying smooth shading with a threshold function. We extend this approach and specify threshold values wit...

A class of enhancement techniques is proposed for images in arbitrary dimension D. They are free from either space/frequency (scale) or grey references. There are two subclasses. One subclass is the chain: {Negative Laplace operator, Multiplication by Power (γ−1) of modulus-Laplace value, Inverse Negative Laplace operator} together with generalized versions. The generalization of the Negative L...

Edit propagation on images/videos has become more and more popular in recent years due to simple and intuitive interaction. It propagates sparse user edits to the whole data following the policy that nearby regions with similar appearances receive similar edits. While it gives a friendly editing mode, it often produces aliasing artifacts on edge pixels. In this paper, we present a simple algori...

Edit propagation on images/videos has become more and more popular in recent years due to simple and intuitive interaction. It propagates sparse user edits to the whole data following the policy that nearby regions with similar appearances receive similar edits. While it gives a friendly editing mode, it often produces aliasing artifacts on edge pixels. In this paper, we present a simple algori...

Agents learning to act in a partially observable domain may need to overcome the problem of perceptual aliasing – i.e., different states that appear similar but require different responses. This problem is exacerbated when the agent’s sensors are noisy, i.e., sensors may produce different observations in the same state. We show that many well-known reinforcement learning methods designed to dea...

In this paper, we propose a way to fuse the image-based localisation approach with the Monte-Carlo localisation approach. The method we propose does not suffer of the major limitation of the two separated methods: the need of a metric map of the environment for the Monte-Carlo localisation and the failure of the image-based approach in environments with spatial periodicity (perceptual aliasing)...