Related papers: Ultrafast Pulse Retrieval from Partial FROG Traces…
The rapid advancement of diffusion models, particularly Stable Diffusion 3.5, has enabled the generation of highly photorealistic synthetic images that pose significant challenges to existing detection methods. This paper presents…
The time-resolved detection of ultrashort pulsed THz-band electric field temporal profiles without an ultrashort laser probe is demonstrated. A non-linear interaction between a narrow-bandwidth optical probe and the THz pulse transposes the…
Ultrafast experiments require precise temporal characterization of laser pulses, where pulse reconstruction is typically achieved through iterative retrieval algorithms. In this context, the amplitude swing technique has emerged as a robust…
Phase unwrapping remains a critical and challenging problem in InSAR processing, particularly in scenarios involving complex deformation patterns. In earthquake-related deformation, shallow sources can generate surface-breaking faults and…
Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used…
Generative diffusion models have emerged as a powerful tool for high-quality image synthesis, yet their iterative nature demands significant computational resources. This paper proposes an efficient time step sampling method based on an…
Recovering high-dimensional statistical structure from limited measurements is a fundamental challenge in hyperspectral imaging, where capturing full-resolution data is often infeasible due to sensor, bandwidth, or acquisition constraints.…
In video editing, the hallmark of a quality edit lies in its consistent and unobtrusive adjustment. Modification, when integrated, must be smooth and subtle, preserving the natural flow and aligning seamlessly with the original vision.…
We investigate the statistical recovery of missing physics and turbulent phenomena in fluid flows using generative machine learning. Here we develop a two-stage super-resolution method using spectral filtering to restore the high-wavenumber…
Diffusion models enable high-quality and diverse visual content synthesis. However, they struggle to generate rare or unseen concepts. To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image…
High peak power ultrafast lasers are widely used in nonlinear spectroscopy but often limit its spectral resolution because of the broad frequency bandwidth of ultrashort laser pulses. Improving the resolution by achieving spectrally narrow…
In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data. However, the existing solutions require either hardware changes or…
Phase retrieval aims to recover a signal from intensity-only measurements, a fundamental problem in many fields such as imaging, holography, optical computing, crystallography, and microscopy. Although there are several well-known phase…
High-fidelity numerical simulations of chaotic, high dimensional nonlinear dynamical systems are computationally expensive, necessitating the development of efficient surrogate models. Most surrogate models for such systems are…
We demonstrate a novel imaging approach and associated reconstruction algorithm for far-field coherent diffractive imaging, based on the measurement of a pair of laterally sheared diffraction patterns. The differential phase profile…
Diffusion probabilistic models have been recently used in a variety of tasks, including speech enhancement and synthesis. As a generative approach, diffusion models have been shown to be especially suitable for imputation problems, where…
3D Gaussian Splatting (3DGS) has become a powerful representation for image-based object reconstruction, yet its performance drops sharply in sparse-view settings. Prior works address this limitation by employing diffusion models to repair…
Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifacts. We introduce Deceptive-NeRF/3DGS to enhance sparse-view…
The generation of ultrafast laser pulses and the reconstruction of their electric fields is essential for many applications in modern optics. Quantum optical fields can also be generated on ultrafast time scales, however, the tools and…
The growing demand for effective spectrum management and interference mitigation in shared bands, such as the Citizens Broadband Radio Service (CBRS), requires robust radar detection algorithms to protect the military transmission from…