Learn More
Photographs taken in low-light conditions are often blurry as a result of camera shake, i.e. a motion of the camera while its shutter is open. Most existing deblurring methods model the observed blurry image as the convolution of a sharp image with a uniform blur kernel. However, we show that blur from camera shake is in general mostly due to the 3D(More)
We address the problem of deblurring images degraded by camera shake blur and saturated (over-exposed) pixels. Saturated pixels violate the common assumption that the image-formation process is linear, and often cause ringing in deblurred outputs. We provide an analysis of ringing in general, and show that in order to prevent ringing, it is insufficient to(More)
Often when we review our holiday photos, we notice things we wish we could have avoided, such as vehicles, construction work, or simply other tourists. We cannot go back and retake the photo, so what can we do if we want to remove these things from our photos? We want to replace these sections of the image in a convincing way, preferably with what would(More)
Sujet de la thèse: Méthodes d'apprentissage de dictionnaire pour la séparation de sources audio avec un seul capteur — Dictionary learning methods for single-channel audio source separation Thèse présentée et soutenuè a Cachan le 4 Octobre 2012 devant le jury composé de: RésuméÉtant donné un mélange de plusieurs signaux sources, par exemple un morceau et(More)
  • Francis Bach, Eric Moulines Professeur, Télécom-Paristech Examinateur, Bruno Olshausen, Rapporteur Jean, Ponce Professeur +57 others
  • 2010
Sujet de la thèse : Représentations parcimonieuses en apprentissage statistique, traitement d'image et vision par ordinateur — Sparse coding for machine learning, image processing and computer vision Thèse présentée et soutenue à Cachan le 30 novembre 2010 devant le jury composé de : abstract Many fields from experimental sciences now deal with a large and(More)
This note outlines the derivation of the parameter update formulas for the variational non-uniform blind deblurring algorithm described in Whyte et al. [4]. First, using the calculus of variations, we find the optimal forms of the factorized approximating distributions and arrive at the same formulas as in the uniform blind deblurring of Miskin & MacKay [3](More)
  • 1