Related papers: Ultra-low-light computer vision using trained phot…
We introduce Adaptive Guided Upsampling (AGU), an efficient method for upscaling low-light images capable of optimizing multiple image quality characteristics at the same time, such as reducing noise and increasing sharpness. It is based on…
This paper describes a completely new way to perform noise rejection using a two-photon sensitive detector and taking advantage of the properties of correlated photons to improve an optical communications link in the presence of…
Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are…
Single-photon detectors are ``blind" after the detection of a photon, and thereafter display a characteristic recovery in efficiency, during which the number of undetected photons depends on the statistics of the incident light. We show how…
In this paper, we propose a novel low-light image enhancement method aimed at improving the performance of recognition models. Despite recent advances in deep learning, the recognition of images under low-light conditions remains a…
Low-light image enhancement is a challenging low-level computer vision task because after we enhance the brightness of the image, we have to deal with amplified noise, color distortion, detail loss, blurred edges, shadow blocks and halo…
Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many…
Conventional LIDAR systems require hundreds or thousands of photon detections to form accurate depth and reflectivity images. Recent photon-efficient computational imaging methods are remarkably effective with only 1.0 to 3.0 detected…
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…
Automatic image colourisation is the computer vision research path that studies how to colourise greyscale images (for restoration). Deep learning techniques improved image colourisation yielding astonishing results. These differ by various…
We propose a novel method to perform plenoptic imaging at the diffraction limit by measuring second-order correlations of light between two reference planes, arbitrarily chosen, within the tridimensional scene of interest. We show that for…
Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification, etc.) by encouraging underlying algorithms to focus on…
Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2) During meta-testing, the acquired knowledge is used to…
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an…
Low-light-level imaging techniques have application in many diverse fields, ranging from biological sciences to security. We demonstrate a single-photon imaging system based on a time-gated inten- sified CCD (ICCD) camera in which the image…
Recently an optical amplification process called the plasmon injection scheme was introduced as an effective solution to overcoming losses in metamaterials. Implementations with near-field imaging applications have indicated substantial…
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the…
Blind deconvolution is a challenging problem, but in low-light it is even more difficult. Existing algorithms, both classical and deep-learning based, are not designed for this condition. When the photon shot noise is strong, conventional…
The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…
Benefiting from the excellent control of single photons realized by the emitter-photon-chiral couplings, we propose a novel potential photonic-quantum-computation scheme to perform the supervised learning tasks. The gates for photonic…