Related papers: Interleaved diffractive networks for information t…
Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…
A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for…
Thanks to the latest advancements in wavefront shaping, optical methods have proven crucial to achieve imaging and control light in multiply scattering media, like biological tissues. However, the stability times of living biological…
An important problem of reconstruction of diffusion network and transmission probabilities from the data has attracted a considerable attention in the past several years. A number of recent papers introduced efficient algorithms for the…
Numerous everyday situations like navigation, medical imaging and rescue operations require viewing through optically inhomogeneous media. This is a challenging task as photons, instead of traversing ballistically, propagate predominantly…
We investigate the potential of mutual scattering, i.e., light scattering with multiple properly phased incident beams, as a method to extract structural information from inside an opaque object. In particular, we study how sensitively the…
In this paper, we present a novel reconstruction method for diffuse optical spectroscopic imaging with a commonly used tissue model of optical absorption and scattering. It is based on linearization and group sparsity, which allows…
Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…
Diffusion models have achieved remarkable image generation quality surpassing previous generative models. However, a notable limitation of diffusion models, in comparison to GANs, is their difficulty in smoothly interpolating between two…
We present an optical picture of linear-optics superradiance, based on a single scattering event embedded in a dispersive effective medium composed by the other atoms. This linear-dispersion theory is valid at low density and in the…
Application-specific optical processors have been considered disruptive technologies for modern computing that can fundamentally accelerate the development of artificial intelligence (AI) by offering substantially improved computing…
Nonlinear computation is essential for a wide range of information processing tasks, yet implementing nonlinear functions using optical systems remains a challenge due to the weak and power-intensive nature of optical nonlinearities.…
In the present work, we explore efficient ways to transmit binary information in discrete, semi-infinite chains of coupled oscillators using the process of nonlinear supratransmission. A previous work showed that such transmission is…
Optical imaging relies on the ability to illuminate an object, collect and analyze the light it scatters or transmits. Propagation through complex media such as biological tissues was so far believed to degrade the attainable depth as well…
We enhanced the total transmission of light through a disordered waveguide with spatially inhomogeneous scattering and loss by shaping the incident wavefront of a laser beam. Using an on-chip tapered lead, we were able to access all input…
We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained…
Diffractive deep neural network (DNNet) is a novel machine learning framework on the modulation of optical transmission. Diffractive network would get predictions at the speed of light. It's pure passive architecture, no additional power…
Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high…
Scattering, especially multiple scattering, is a well known problem in imaging, ranging from astronomy to medicine. In particular it is often desirable to be able to perform non-invasive imaging through turbid and/or opaque media. Many…