BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Département de mathématiques et applications - ECPv6.2.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.math.ens.psl.eu
X-WR-CALDESC:évènements pour Département de mathématiques et applications
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20250204T110000
DTEND;TZID=Europe/Paris:20250204T120000
DTSTAMP:20260524T004018
CREATED:20250203T121353Z
LAST-MODIFIED:20250203T121354Z
UID:18936-1738666800-1738670400@www.math.ens.psl.eu
SUMMARY:Séminaire des doctorants / post-doctorants du CSD : Nathanaël Cuvelle--Magar
DESCRIPTION:Title: Optimal denoising of geometrically regular images with scattering coefficients\n  \nAbstract: Optimal suppression of additive Gaussian white noise has many image processing applications and is a key step to generate images with score diffusion algorithms. For images with edges that are piecewise regular\, nearly optimal denoisers can be computed by thresholding a sparse representation in a dictionary of curvelets or bandlets. It requires to adapt the support of selected dictionary vectors to geometric image properties. In contrast\, convolutional deep neural networks can implement optimal denoising algorithms with a cascade of fixed support filters and non-linearities. It also applies to much more complex images. An outstanding issue is to understand how convolutional neural networks can reach optimal results\, without adapting their filter support. We show that a two layer network with fixed wavelet filters can disentangle geometric support constraints. This scattering transform explains why filter supports do not need to be adapted to the image geometry. For piecewise regular images having piecewise regular edges\, numerical results are asymptotically optimal. This is supported by a characterisation of the scattering coefficient decay\, but this denoising optimality remains a mathematical conjecture.\n 
URL:https://www.math.ens.psl.eu/evenement/seminaire-des-doctorants-post-doctorants-du-csd-nathanael-cuvelle-magar/
LOCATION:CSD Conference room
CATEGORIES:CSD seminar
END:VEVENT
END:VCALENDAR