Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Statistics for Spatial Data.

Elements of Information Theory (2nd ed.). Thomas M. Cover and Joy A. Thomas

In this paper we describe a novel technique for detecting salient regions in an image. The detector is a generalization to affine invariance of the method introduced by Kadir and Brady [10]. The detector deems a region salient if it exhibits unpredictability in both its attributes and its spatial scale.

An affine invariant salient region detector

Flattening the Earth, Two Thousand Years of Map Projections

In a multiview-imaging setting, image-acquisition costs could be substantially diminished if some of the cameras operate at a reduced quality. Compressed sensing is proposed to effectuate such a reduction in image quality wherein certain images are acquired with random measurements at a reduced sampling rate via projection onto a random basis of lower dimension. To recover such projected images, compressed-sensing recovery incorporating disparity compensation is employed. Based on a recent compressed-sensing recovery algorithm for images that couples an iterative projection-based reconstruction with a smoothing step, the proposed algorithm drives image recovery using the projection-domain residual between the random measurements of the image in question and a disparity-based prediction created from adjacent, high-quality images. Experimental results reveal that the disparity-based reconstruction significantly outperforms direct reconstruction using simply the random measurements of the image alone.

/pdf/disparity-compensated-compressed-sensing-reconstruction-for-gl1uf4fjyi.pdf

Disparity-compensated compressed-sensing reconstruction for multiview images

In this paper, we propose a new geometry representation method for multiview image sets. Our approach relies on graphs to describe the multiview geometry information in a compact and controllable way. The links of the graph connect pixels in different images and describe the proximity between pixels in 3D space. These connections are dependent on the geometry of the scene and provide the right amount of information that is necessary for coding and reconstructing multiple views. Our multiview image representation is very compact and adapts the transmitted geometry information as a function of the complexity of the prediction performed at the decoder side. To achieve this, our graph-based representation (GBR) carefully selects the amount of geometry information needed before coding. This is in contrast with depth coding, which directly compresses with losses the original geometry signal, thus making it difficult to quantify the impact of coding errors on geometry-based interpolation. We present the principles of this GBR and we build an efficient coding algorithm to represent it. We compare our GBR approach to classical depth compression methods and compare their respective view synthesis qualities as a function of the compactness of the geometry description. We show that GBR can achieve significant gains in geometry coding rate over depth-based schemes operating at similar quality. Experimental results demonstrate the potential of this new representation.

/pdf/graph-based-representation-for-multiview-image-geometry-3nnaza6328.pdf

Graph-Based Representation for Multiview Image Geometry

Distributed video coding performances strongly depend on the side information quality, built at the decoder. In multi-view schemes, correlations in both time and view directions are exploited, obtaining in general two estimations that need to be merged. This step, called fusion, greatly affects the performance of the coding scheme; however, the existing methods do not achieve acceptable performances in all cases, especially when one of the estimations is not of good quality, since in this case they are not able to discard it. This paper provides a detailed review of existing fusion methods between temporal and inter-view side information, and proposes new promising techniques. Experimental results show that these methods have good performances in a variety of configurations.

Fusion schemes for multiview distributed video coding

Omnidirectional images describe the color information at a given position from all directions. Affordable 360° cameras have recently been developed leading to an explosion of the 360° data shared on social networks. However, an omnidirectional image does not contain interesting content everywhere. Some part of the images are indeed more likely to be looked at by some users than others. Knowing these regions of interest might be useful for 360° image compression, streaming, retargeting or even editing. In this paper, we aim at modelling the user navigation within a 360° image, and detecting which parts of an omnidirectional content might draw users' attention. In particular, the paper proposes to aggregate and analyze 2D saliency detectors in different map projections, and also proposes a smooth navigation through the image to maximize saliency.

Saliency-based navigation in omnidirectional image

Compressed sensing is applied to multiview image sets and inter-image disparity compensation is incorporated into image reconstruction in order to take advantage of the high degree of inter-image correlation common to multiview scenarios. Instead of recovering images in the set independently from one another, two neighboring images are used to calculate a prediction of a target image, and the difference between the original measurements and the compressed-sensing projection of the prediction is then reconstructed as a residual and added back to the prediction in an iterated fashion. The proposed method shows large gains in performance over straightforward, independent compressed-sensing recovery. Additionally, projection and recovery are block-based to significantly reduce computation time.

/pdf/compressed-sensing-of-multiview-images-using-disparity-2k50z7mpby.pdf

Thomas Maugey

Papers

Disparity-compensated compressed-sensing reconstruction for multiview images

Graph-Based Representation for Multiview Image Geometry

Fusion schemes for multiview distributed video coding

Saliency-based navigation in omnidirectional image

Compressed sensing of multiview images using disparity compensation