Related papers: Spatially Addressable Readout and Erasure of an Im…

We present a quantum memory protocol that allows to store light in ensembles of two-level atoms, e.g. rare-earth ions doped into a crystal, by modulating the refractive index of the host medium of the atoms linearly in time. We show that…

The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious…

This work prioritizes building a modular pipeline that utilizes existing models to systematically restore images, rather than creating new restoration models from scratch. Restoration is carried out at an object-specific level, with each…

Designing nanophotonic structures traditionally grapples with the complexities of discrete parameters, such as real materials, often resorting to costly global optimization methods. This paper introduces an approach that leverages…

We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by…

Large scale quantum information processing requires stable and long-lived quantum memories. Here, using atom-photon entanglement, we propose an experimentally feasible scheme to realize decoherence-free quantum memory with atomic ensembles,…

The alignment of serial-section electron microscopy (ssEM) images is critical for efforts in neuroscience that seek to reconstruct neuronal circuits. However, each ssEM plane contains densely packed structures that vary from one section to…

In this paper, we propose a novel scheme for scalable image coding based on the concept of epitome. An epitome can be seen as a factorized representation of an image. Focusing on spatial scalability, the enhancement layer of the proposed…

We have analyzed an efficient integration of the multi-qubit echo quantum memory into the quantum computer scheme on the atomic resonant ensembles in quantum electrodynamics cavity. Here, one atomic ensemble with controllable inhomogeneous…

Purpose: Develop a processing scheme for Gradient Echo (GRE) phase to enable restoration of susceptibility-related (SuR) features in regions affected by imperfect phase unwrapping, background suppression and low signal-to-noise ratio (SNR)…

A novel algorithm for tunable compression to within the precision of reproduction targets, or storage, is proposed. The new algorithm is termed the `Perceptron Algorithm', which utilises simple existing concepts in a novel way, has multiple…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

A simple method of phase-and-amplitude extraction is derived that corrects for image blurring induced by partially spatially coherent incident illumination using only a single intensity image as input. The method is based on Fresnel…

We present a novel diffractive imaging method that harnesses a low-resolution real-space image to guide the phase retrieval. A computational algorithm is developed to utilize such prior knowledge as a real-space constraint in the iterative…

Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak…

Interferometers are widely used in imaging technologies to achieve enhanced spatial resolution, but require that the incoming photons be indistinguishable. In previous work, we built and analyzed color erasure detectors which expand the…

Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images. Spatial-domain information has been widely exploited to implement image SR, so a new trend is to involve frequency-domain…

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic…

Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for…

Learned image compression methods have shown superior rate-distortion performance and remarkable potential compared to traditional compression methods. Most existing learned approaches use stacked convolution or window-based self-attention…