Publications related to Sparse Gradient Image Reconstruction from Incomplete Fourier Measurements and Prior Edge Information

Daylight illuminant retrieval using redundant image elements

We present a method for retrieving illuminant spectra from a set of images taken with a fixed location camera, such as a surveillance or panoramic one. In these images, there will be significant changes in lighting conditions and scene content, but there w ...

2010

Propagation of geotags based on object duplicate detection

Touradj Ebrahimi, Jong Seok Lee, Lutz Goldmann, Ivan Ivanov, Péter Vajda

In this paper, we consider the use of object duplicate detection for the propagation of geotags from a small set of images with location names (IPTC) to a large set of non-tagged images. The motivation behind this idea is that images of individual location ...

Spie-Int Soc Optical Engineering, Po Box 10, Bellingham, Wa 98227-0010 Usa2010

Compressive Sensing of Localized Signals: Application to Analog-to-Information Conversion

Juri Ranieri

Compressed sensing hinges on the sparsity of signals to allow their reconstruction starting from a limited number of measures. When reconstruction is possible, the SNR of the reconstructed signal depends on the energy collected in the acquisition. Hence, i ...

2010

On unifying sparsity and geometry for image-based 3D scene representation

Ivana Tosic

Demand has emerged for next generation visual technologies that go beyond conventional 2D imaging. Such technologies should capture and communicate all perceptually relevant three-dimensional information about an environment to a distant observer, providin ...

EPFL2009

Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms

Pierre Vandergheynst, Rémi Gribonval, Karin Schnass

This paper provides new results on computing simultaneous sparse approximations of multichannel signals over redundant dictionaries using two greedy algorithms. The first one, p-thresholding, selects the S atoms that have the largest

p

-correlation while ...

2008

Illuminant retrieval for fixed location cameras

Sabine Süsstrunk, Joanna Marguier

Fixed location cameras, such as panoramic cameras or surveillance cameras, are very common. In images taken with these cameras, there will be changes in lighting and dynamic image content, but there will also be constant objects in the background. We propo ...

2008

A collaborative approach to image segmentation and behavior recognition from image sequences

Laura Ioana Gui

Visual behavior recognition is currently a highly active research area. This is due both to the scientific challenge posed by the complexity of the task, and to the growing interest in its applications, such as automated visual surveillance, human-computer ...

EPFL2008

Compressed Sensing For Multi-View Tracking And 3-D Voxel Reconstruction

Volkan Cevher

Compressed sensing (CS) suggests that a signal, sparse in some basis, can be recovered from a small number of random projections. In this paper, we apply the CS theory on sparse background-subtracted silhouettes and show the usefulness of such an approach ...

2008

Coarse scene geometry estimation from sparse approximations of multi-view omnidirectional images

Pascal Frossard, Ivana Tosic

This paper presents a framework for coarse scene geometry estimation, based on sparse representations of omnidirectional images with geometrical basis functions. We introduce a correlation model that relates sparse components in different views with local ...

2007

Joint Demosaicing and Super-Resolution Imaging from a Set of Unregistered Aliased Images

Sabine Süsstrunk, Patrick Vandewalle, Karim Krichane

We present a new algorithm that performs demosaicing and super-resolution jointly from a set of raw images sampled with a color filter array. Such a combined approach allows us to compute the alignment parameters between the images on the raw camera data b ...

2007

Sparse Gradient Image Reconstruction from Incomplete Fourier Measurements and Prior Edge Information

Graph Chatbot

Chat with Graph Search

Daylight illuminant retrieval using redundant image elements

Propagation of geotags based on object duplicate detection

Compressive Sensing of Localized Signals: Application to Analog-to-Information Conversion

On unifying sparsity and geometry for image-based 3D scene representation

Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms

Illuminant retrieval for fixed location cameras

A collaborative approach to image segmentation and behavior recognition from image sequences

Compressed Sensing For Multi-View Tracking And 3-D Voxel Reconstruction

Coarse scene geometry estimation from sparse approximations of multi-view omnidirectional images

Joint Demosaicing and Super-Resolution Imaging from a Set of Unregistered Aliased Images

Daylight illuminant retrieval using redundant image elements

Propagation of geotags based on object duplicate detection

On unifying sparsity and geometry for image-based 3D scene representation

Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms

Compressed Sensing For Multi-View Tracking And 3-D Voxel Reconstruction

Illuminant retrieval for fixed location cameras

A collaborative approach to image segmentation and behavior recognition from image sequences

Coarse scene geometry estimation from sparse approximations of multi-view omnidirectional images

Joint Demosaicing and Super-Resolution Imaging from a Set of Unregistered Aliased Images

Compressive Sensing of Localized Signals: Application to Analog-to-Information Conversion