The richness of natural images makes the quest for optimal representations in image processing and computer vision challenging. The latter observation has not prevented the design of image representations, which trade off between efficiency and complexity, while achieving accurate rendering of smooth regions as well as reproducing faithful contours and textures. The most recent ones, proposed in the past decade, share an hybrid heritage highlighting the multiscale and oriented nature of edges and patterns in images. This paper presents a panorama of the aforementioned literature on decompositions in multiscale, multi-orientation bases or dictionaries. They typically exhibit redundancy to improve sparsity in the transformed domain and sometimes its invariance with respect to simple geometric deformations (translation, rotation). Oriented multiscale dictionaries extend traditional wavelet processing and may offer rotation invariance. Highly redundant dictionaries require specific algorithms to simplify the search for an efficient (sparse) representation. We also discuss the extension of multiscale geometric decompositions to non-Euclidean domains such as the sphere or arbitrary meshed surfaces. The etymology of panorama suggests an overview, based on a choice of partially overlapping “pictures”.

Extracting good representations from images is essential for many computer vision tasks. In this paper, we propose hierarchical matching pursuit (HMP), which builds a feature hierarchy layer-by-layer using an efficient matching pursuit encoder. It includes three modules: batch (tree) orthogonal matching pursuit, spatial pyramid max pooling, and contrast normalization. We investigate the architecture of HMP, and show that all three components are critical for good performance. To speed up the orthogonal matching pursuit, we propose a batch tree orthogonal matching pursuit that is particularly suitable to encode a large number of observations that share the same large dictionary. HMP is scalable and can efficiently handle full-size images. In addition, HMP enables linear support vector machines (SVM) to match the performance of nonlinear SVM while being scalable to large datasets. We compare HMP with many state-of-the-art algorithms including convolutional deep belief networks, SIFT based single layer sparse coding, and kernel based feature learning. HMP consistently yields superior accuracy on three types of image classification problems: object recognition (Caltech-101), scene recognition (MIT-Scene), and static event recognition (UIUC-Sports). 1

Hyperspectral imaging is a promising tool for applications in geosensing, cultural heritage and beyond. However, compared to current RGB cameras, existing hyperspectral cameras are severely limited in spatial resolution. In this paper, we introduce a simple new technique for reconstructing a very high-resolution hyperspectral image from two readily obtained measurements: A lower-resolution hyperspectral image and a high-resolution RGB image. Our approach is divided into two stages: We first apply an unmixing algorithm to the hyperspectral input, to estimate a basis representing reflectance spectra. We then use this representation in conjunction with the RGB input to produce the desired result. Our approach to unmixing is motivated by the spatial sparsity of the hyperspectral input, and casts the unmixing problem as the search for a factorization of the input into a basis and a set of maximally sparse coefficients. Experiments show that this simple approach performs reasonably well on both simulations and real data examples. 1.

In this paper, we present dictionary learning methods for sparse and redundant signal representations in high dimensional feature space. Using the kernel method, we describe how the well-known dictionary learning approaches such as the method of optimal directions and K-SVD can be made nonlinear. We analyze these constructions and demonstrate their improved performance through several experiments on classification problems. It is shown that nonlinear dictionary learning approaches can provide better discrimination compared to their linear counterparts and kernel PCA, especially when the data is corrupted by noise. Index Terms — Kernel methods, dictionary learning, method of optimal directions, K-SVD. 1.

Abstract — We introduce the concept of using compressive sensing techniques to provide feedback in order to control dynamical systems. Compressive sensing algorithms use l1regularization for reconstructing data from a few measurement samples. These algorithms provide highly efficient reconstruction for sparse data. For data that is not sparse enough, the reconstruction technique produces a bounded error in the estimate. In a dynamical system, such erroneous stateestimation can lead to undesirable effects in the output of the plant. In this work, we present some techniques to overcome the aforementioned restriction. Our efforts fall into two main categories. First, we present some techniques to design feedback systems that sparsify the state in order to perfectly reconstruct it using compressive sensing algorithms. We study the effect of such sparsification schemes on the stability and regulation of the plant. Second, we study the characteristics of dynamical systems that produce sparse states so that compressive sensing techniques can be used for feedback in such scenarios without any additional modification in the feedback loop. I.

Over the past decade there has been a great interest in a synthesis-based model for signals, based on sparse and redundant representations. Such a model assumes that the signal of interest can be decomposed as a linear combination of few columns from a given matrix (the dictionary). An alternative, analysis-based, model can be envisioned, where an analysis operator multiplies the signal, leading to a sparse outcome. In this paper we propose a simple but effective analysis operator learning algorithm, where analysis “atoms” are learned sequentially by identifying directions that are orthogonal to a subset of the training data. We demonstrate the effectiveness of the algorithm in three experiments, treating synthetic data and real images, showing a successful and meaningful recovery of the analysis operator. 1.

Abstract—We propose a novel regularization method for sparse image reconstruction from compressive measurements. The approach relies on the conjecture that natural images exhibit strong average sparsity over multiple coherent frames. The associated reconstruction algorithm, based on an analysis prior and a reweighted ℓ1 scheme, is dubbed Sparsity Averaging Reweighted Analysis (SARA). We test our prior and the associated algorithm through extensive numerical simulations for spread spectrum and Gaussian acquisition schemes suggested by the recent theory of compressed sensing with coherent and redundant dictionaries. Our results show that average sparsity outperforms state-of-theart priors that promote sparsity in a single orthonormal basis or redundant frame, or that promote gradient sparsity. We also illustrate the performance of SARA in the context of Fourier imaging, for particular applications in astronomy and medicine. Index Terms—Compressed sensing, sparse approximation, image reconstruction, wavelet representation. I.

Great advancements in commodity graphics hardware have favored GPU-based volume rendering as the main adopted solution for interactive exploration of rectilinear scalar volumes on commodity platforms. Nevertheless, long data transfer times and GPU memory size limitations are often the main limiting factors, especially for massive, time-varying or multi-volume visualization, or for networked visualization on the emerging mobile devices. To address this issue, a variety of level-of-detail data representations and compression techniques have been introduced. In order to improve capabilities and performance over the entire storage, distribution and rendering pipeline, the encoding/decoding process is typically highly asymmetric, and systems should ideally compress at data production time and decompress on demand at rendering time. Compression and level-of-detail pre-computation does not have to adhere to real-time constraints and can be performed off-line for high quality results. In contrast, adaptive real-time rendering from compressed representations requires fast, transient, and spatially independent decompression. In this report, we review the existing compressed GPU volume rendering approaches, covering compact representation models, compression techniques, GPU rendering architectures and fast decoding techniques.