IEEE Transactions on Computational Imaging

Robustness and stability of image-reconstruction algorithms have recently come under scrutiny. Their importance to medical imaging cannot be overstated. We review the known results for the topical variational regularization strategies ( ℓ2 and ℓ1 regularization) and present novel stability results for ℓp -regularized linear inverse problems for p∈(1,∞) . Our results guarantee Lipschitz continuity for small p and Hölder continuity for larger p . They generalize well to the Lp (Ω)  function spaces.

Spatial-angular separable convolution (SAS-conv) has been widely used for efficient and effective 4D light field (LF) feature embedding in different tasks, which mimics a 4D convolution by alternatively operating on 2D spatial slices and 2D angular slices. In this paper, we argue that, despite its global intensity modeling capabilities, SAS-conv can only embed local geometry information into the features, resulting in inferior performances in the regions with textures and occlusions. Because the epipolar lines are highly related to the scene depth, we introduce the concept of spatial-angular correlated convolution (SAC-conv).

Hyperspectral imaging (HSI) has become an invaluable imaging tool for many applications in astrophysics or Earth observation. Unfortunately, direct observation of hyperspectral images is impossible since the actual measurements are 2-D and suffer from strong spatial and spectral degradations, especially in the infrared.

Superpixel provides local pixel coherence and respects object boundary, which is beneficial to stereo matching. Recently, superpixel cues are introduced into deep stereo networks. These methods develop a superpixel-based sampling scheme to downsample input color images and upsample output disparity maps. However, in this way, the image details are inevitably lost in the downsampling and the upsampling process introduces errors in the final disparity as well. Besides, this mechanism further limits the possibility of utilizing larger and multi-scale superpixels, which are important to alleviate the matching ambiguity.

We introduce an efficient synthetic electrode selection strategy for use in Adaptive Electrical Capacitance Volume Tomography (AECVT). The proposed strategy is based on the Adaptive Relevance Vector Machine (ARVM) method and allows to successively obtain synthetic electrode configurations that yield the most decrease in the image reconstruction uncertainty for the spatial distribution of the permittivity in the region of interest. 

In this paper, we explore the spatiospectral image super-resolution (SSSR) task, i.e., joint spatial and spectral super-resolution, which aims to generate a high spatial resolution hyperspectral image (HR-HSI) from a low spatial resolution multispectral image (LR-MSI). To tackle such a severely ill-posed problem, one straightforward but inefficient way is to sequentially perform a single image super-resolution (SISR) network followed by a spectral super-resolution (SSR) network in a two-stage manner or reverse order.

Conventional digital cameras typically accumulate all the photons within an exposure period to form a snapshot image. It requires the scene to be quite still during the imaging time, otherwise it would result in blurry image for the moving objects. Recently, a retina-inspired spike camera has been proposed and shown great potential for recording high-speed motion scenes. Instead of capturing the visual scene by a single snapshot, the spike camera records the dynamic light intensity variation continuously.

In this work, a new nonlinear framework is presented for superior reconstructions in ultrasound-modulated optical tomography. The framework is based on minimizing a functional comprising of least squares data fitting term along with additional sparsity priors that promote high contrast, subject to the photon-propagation diffusion equation. The resulting optimization problem is solved using a sequential quadratic Hamiltonian scheme, based on the Pontryagin’s maximum principle, that does not involve semi-smooth calculus and is easy to implement.

In this paper, we propose a new design for single sensor compressive HDR light field cameras, combining multi-ISO photography with coded mask acquisition, placed in a compressive sensing framework. The proposed camera model is based on a main lens, a multi-ISO sensor and a coded mask located in the optical path between the main lens and the sensor that projects the coded spatio-angular information of the light field onto the 2D sensor. The model encompasses different acquisition scenarios with different ISO patterns and gains.

We propose Coordinate-based Internal Learning (CoIL) as a new deep-learning (DL) methodology for continuous representation of measurements. Unlike traditional DL methods that learn a mapping from the measurements to the desired image, CoIL trains a multilayer perceptron (MLP) to encode the complete measurement field by mapping the coordinates of the measurements to their responses. CoIL is a self-supervised method that requires no training examples besides the measurements of the test object itself.