Related papers: Optical information transfer through random unknow…
Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep…
Text-to-image diffusion models (T2I) use a latent representation of a text prompt to guide the image generation process. However, the process by which the encoder produces the text representation is unknown. We propose the Diffusion Lens, a…
End-to-end optimization, which simultaneously optimizes optics and algorithms, has emerged as a powerful data-driven method for computational imaging system design. This method achieves joint optimization through backpropagation by…
Distributing entangled photon pairs over noisy channels is an important task for various quantum information protocols. Encoding an entangled state in a decoherence-free subspace (DFS) formed by multiple photons is a promising way to…
Recent fast style transfer methods use a pre-trained convolutional neural network as a feature encoder and a perceptual loss network. Although the pre-trained network is used to generate responses of receptive fields effective for…
Diffractive optical networks unify wave optics and deep learning to all-optically compute a given machine learning or computational imaging task as the light propagates from the input to the output plane. Here, we report the design of…
Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…
Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…
Modeling radio frequency (RF) signal propagation is essential for understanding the environment, as RF signals offer valuable insights beyond the capabilities of RGB cameras, which are limited by the visible-light spectrum, lens coverage,…
Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…
The transfer of quantum information through a noisy environment is a central challenge in the fields of quantum communication, imaging and nanophotonics. In particular, high-dimensional quantum states of light enable quantum networks with…
In optical communications, logical bits are encoded in physical degrees-of-freedom (DoFs) of the electromagnetic field. Consequently, optical scattering in a communications channel compromises the information transfer. In the…
In turbid media, scattering of light scrambles information of the incident beam and represents an obstacle to optical imaging. Noninvasive imaging through opaque layers is challenging for dynamic and wide-field objects due to unreliable…
This paper introduces a deep learning approach to dynamic spectrum access, leveraging the synergy of multi-modal image and spectrum data for the identification of potential transmitters. We consider an edge device equipped with a camera…
Scattering in complex media scrambles light, thus obscuring images and limiting applications from astronomy to microscopy. Existing computational and wavefront-shaping methods treat scattering as a linear optical-wave inversion problem that…
Recent advances in image generation have made diffusion models powerful tools for creating high-quality images. However, their iterative denoising process makes understanding and interpreting their semantic latent spaces more challenging…
Artificial intelligence has emerged as promising tool to decode a phase image transmitted through a multimode fiber (MMF) by applying deep learning techniques. By transmitting tens of thousands of images through the MMF, deep neural…
Deformable image registration aims to precisely align medical images from different modalities or times. Traditional deep learning methods, while effective, often lack interpretability, real-time observability and adjustment capacity during…
We dispersively interface an ensemble of one thousand atoms trapped in the evanescent field surrounding a tapered optical nanofiber. This method relies on the azimuthally-asymmetric coupling of the ensemble with the evanescent field of an…
Vision-based perception and reasoning is essential for scene understanding in any autonomous system. RGB and depth images are commonly used to capture both the semantic and geometric features of the environment. Developing methods to…