Related papers: Bayer-type Vis-NIR Routing via Inverse Design for …
Portable backscatter imaging systems (PBI) integrate an X-ray source and detector in a single unit, utilizing Compton scattering photons to rapidly acquire superficial or shallow structural information of an inspected object through…
Capturing visual image with a hyperspectral camera has been successfully applied to many areas due to its narrow-band imaging technology. Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by…
Underwater imaging often suffers from significant visual degradation, which limits its suitability for subsequent applications. While recent underwater image enhancement (UIE) methods rely on the current advances in deep neural network…
New, high-resolution CMOS image sensors for mobile phones have moved beyond the single-binnable Quad Bayer and RGBW-Kodak patterns to the double binnable Hexadeca Bayer pattern featuring 4x4 tiles of like-colored pixels. Pixel binning…
Conventional image sensors are only responsive to the intensity variation of the incoming light wave. By encoding the wavefront information into the balanced detection scheme, we demonstrate an image sensor pixel design that is capable to…
The design of metamaterials which support unique optical responses is the basis for most thin-film nanophotonics applications. In practice this inverse design problem can be difficult to solve systematically due to the large design…
We demonstrate chip-scale flat-top filters at near-infrared wavelengths using negative index photonic crystal based Mach Zehnder interferometers. Supported by full three-dimensional numerical simulations, we experimentally demonstrate a new…
Current research in iris recognition is moving towards enabling more relaxed acquisition conditions. This has effects on the quality of acquired images, with low resolution being a predominant issue. Here, we evaluate a super-resolution…
Shape- and scale-selective digital-filters, with steerable finite/infinite impulse responses (FIR/IIRs) and non-recursive/recursive realizations, that are separable in both spatial dimensions and adequately isotropic, are derived. The…
Joint source-channel coding schemes based on deep neural networks (DeepJSCC) have recently achieved remarkable performance for wireless image transmission. However, these methods usually focus only on the distortion of the reconstructed…
Virtual Reality (VR) has the potential of becoming the next ubiquitous computing platform. Continued progress in the burgeoning field of VR depends critically on an efficient computing substrate. In particular, DRAM access energy is known…
Multi-sensor fusion is widely used in the environment perception system of the autonomous vehicle. It solves the interference caused by environmental changes and makes the whole driving system safer and more reliable. In this paper, a novel…
This paper introduces a novel method to simultaneously super-resolve and colour-predict images acquired by snapshot mosaic sensors. These sensors allow for spectral images to be acquired using low-power, small form factor, solid-state CMOS…
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that…
Inverse rendering remains a core challenge in graphics and vision, especially in the snapshot configurations required for lightweight desktop workflows, where the per-frame information budget is highly constrained. Previous inverse…
Learning-based single image super-resolution (SISR) methods are continuously showing superior effectiveness and efficiency over traditional model-based methods, largely due to the end-to-end training. However, different from model-based…
Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural…
Recent GAN-based image inpainting approaches adopt an average strategy to discriminate the generated image and output a scalar, which inevitably lose the position information of visual artifacts. Moreover, the adversarial loss and…
To enable non-line-of-sight (NLoS) sensing and communications, dual-function radar-communications (DFRC) systems have recently proposed employing reconfigurable intelligent surface (RIS) as a reflector in wireless media. However, in the…
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with…