Consensus Convolutional Sparse Coding

Abstract

Evaluation Mathematical FrameworkConvolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaicking and 4D light field view synthesis.

Sparse representation of visual data for compression and compressed sensing

“…Recently, Convolutional Sparse Coding (CSC) algorithms have attracted a lot of attention for solving inverse problems in image processing. The CSC algorithm was introduced in [404], and several methods have been proposed for improving the efficiency of the algorithm [399,405,406,407,408]. In Fig.…”

Compact snapshot hyperspectral imaging with diffracted rotation

“…A common characteristic of these approaches is the tradeoff between spatial resolution and spectral accuracy in the reconstructed results. To mitigate this tradeoff, Choi et al [2017] proposed a data-driven prior trained using an autoencoder network, and Choudhury et al [2017] exploit convolutional sparse coding as a hyperspectral prior. They reduce the ill-posedness of the problem by means of data-driven representations of natural hyperspectral images.…”

Generalized Convolutional Sparse Coding With Unknown Noise

“…Therefore, no pre-processing or postprocessing are needed, and the sample can be optimized as a whole and represented as the sum of a set of filters from the dictionary convolved with the corresponding codes. It has been successfully used on various data types, including trajectories [6], images [7], audios [8], videos [9], multi-spectral and light field images [10] and biomedical data [11], [12], [13], [14]. It also succeeds on a variety of applications accompanying the data, such as recovering non-rigid structure from motion [6], image super resolution [15], image denoising and inpainting [10], music transcription [8], video deblurring [9], neuronal assembly detection [16] and so on.…”

“…ConvCoD [19] uses stochastic gradient descent for dictionary update and additionally learns an encoder to output the codes. Recently, other works [7], [9], [20], [21], [22], [23] use alternating direction method of multipliers (ADMM) [24]. ADMM is favored since it can decompose the subproblem into smaller ADMM subproblems which usually have closed-form solutions.…”