Andrés Almansa

TL;DR: In this article, an automatic video inpainting algorithm which relies on the optimization of a global, patch-based functional is proposed to deal with a variety of challenging situations, such as the correct reconstruction of dynamic textures, multiple moving objects, and moving background.

TL;DR: This work develops a new detection algorithm that relies on the Helmoltz principle, which leads to a vanishing point detector with a low false alarms rate and a high precision level, which does not rely on any a priori information on the image or calibration parameters, and does not require any parameter tuning.

TL;DR: This work presents two mechanisms for processing fingerprint images; shape-adapted smoothing based on second moment descriptors and automatic scale selection based on normalized derivatives, which makes it possible to resolve fine scale structures in clear areas while reducing the risk of enhancing noise in blurred or fragmented areas.

TL;DR: A total variation based restoration model which incorporates the image acquisition model z=h*U+n (where z represents the observed sampled image, U is the ideal undistorted image, h denotes the blurring kernel and n is a white Gaussian noise) as a set of local constraints to express the fact that the variance of the noise can be estimated from the residuals z−h* U if the authors use a neighborhood of each pixel.

TL;DR: An automatic video inpainting algorithm which relies on the optimisation of a global, patch-based functional and requires no segmentation or manual input, and can deal with a wider variety of situations than is handled by previous work.