Abstract: GIF’s local property causes halo artifacts near edges. Recently, a weighted guided image filter (WGIF) with edge-aware weighting was proposed to compensate. Local and global operations improve edge-preserving performance. These guided filters neglect edge…
Abstract: Spectral-spatial transforms (SSTs) convert a raw camera image captured using a color filter array (CFA-sampled image) from an RGB color space composed of red, green, and blue components into a decorrelated color space, such…
Abstract: Unsupervised Domain Adaptation compensates for domain shifts on Electron Microscopy volumes. Our method aggregates visual correspondences—motifs that are visually similar across acquisitions—to infer changes on pretrained model parameters and enable them to operate on…
Abstract: New variational model for non-linear image fusion. Our method uses an osmosis energy term similar to Vogel et al. and Weickert. Minimizing the proposed non-convex energy achieves visually plausible image data fusion invariant to…
Abstract: Two or more chemical dyes stain most whole-slide histological images. Slide stain separation or color deconvolution is essential in digital pathology. This paper formulates the Bayesian blind color deconvolution problem. From a multi-stained histological…
Abstract: Computer vision requires appropriate image representations. Rotation-invariant feature learning has been proposed using RBM extensions. In this paper, we present an extended novel RBM that explicitly factors for rotation nuisance in 2D image inputs…
Abstract: Light field image (LFI) quality assessment is becoming more important to guide immersive media acquisition, processing, and use. Due to LFI’s high dimensionality, quality assessment must consider quality degradation in both spatial and angular…
Abstract: Single image super-resolution (SISR) is a difficult inverse problem because it requires reconstructing high-frequency details from low-resolution images. Most CNN-based super-resolution (SR) methods directly learn the mapping from low-resolution to high-resolution using complex convolutional…
Abstract: Our semi-supervised learning algorithm for single image dehazing works well. The algorithm uses a deep CNN with supervised and unsupervised learning branches. In the supervised branch, mean squared, perceptual, and adversarial losses constrain the…
Abstract: The Mumford-Shah model, a standard image segmentation model, has many approximations due to its difficulty. This functional allows image restoration and contour detection. We propose a general formulation of the discrete counterpart of the…
Abstract: Electromagnetic brain imaging reconstructs brain activity from non-invasive magnetic fields and electric potentials. This imaging modality struggles to estimate source number, location, and time course, especially for distributed brain sources with complex spatial extent….
Abstract: Deep convolutional neural networks (CNNs) have improved RGB-induced salient object detection due to their superior feature learning. Cluttered backgrounds, low light, and lighting variations make such detections difficult. This paper uses thermal infrared images…
WhatsApp us