相关论文: Adaptive Inverse Mapping: A Model-free Semi-superv…

In this work, we focus on the inverse medium scattering problem (IMSP), which aims to recover unknown scatterers based on measured scattered data. Motivated by the efficient direct sampling method (DSM) introduced in [23], we propose a…

This paper is concerned with the inverse scattering problem by an unbounded rough surface. A direct imaging method is proposed to reconstruct the rough surface from the scattered near-field Cauchy data generating by point sources and…

With the commissioning of the refurbished adaptive secondary mirror (ASM) for the 6.5-meter MMT Observatory under way, special consideration had to be made to properly calibrate the mirror response functions to generate an interaction…

Full-field imaging through scattering media is fraught with many challenges. Despite many achievements in recent years, current imaging methods are too slow to deal with fast dynamics that occur for example in biomedical imaging. Here we…

In this work, we study the task of sketch-guided image inpainting. Unlike the well-explored natural language-guided image inpainting, which excels in capturing semantic details, the relatively less-studied sketch-guided inpainting offers…

The demand for inverse design is increasing as the ability to fabricate sub-10 nm features expands the design space by orders of magnitude. Efficient inverse design benefits from differentiable models of light-structure interaction. While…

Despite all recent progress, it is still challenging to edit and manipulate natural images with modern generative models. When using Generative Adversarial Network (GAN), one major hurdle is in the inversion process mapping a real image to…

Image reconstruction plays a critical role in the implementation of all contemporary imaging modalities across the physical and life sciences including optical, MRI, CT, PET, and radio astronomy. During an image acquisition, the sensor…

Space-time varying media with moving interfaces unlock new ways to manipulate electromagnetic waves. Yet, analytical solutions have been mostly limited to interfaces moving at constant velocity or constant proper acceleration. Here, we…

Additive manufacturing is an expanding multidisciplinary field encompassing applications including medical devices, aerospace components, microfabrication strategies, and artificial organs. Among additive manufacturing approaches,…

We study the problem of passive imaging through convolutive channels. A scene is illuminated with an unknown, unstructured source, and the measured response is the convolution of this source with multiple channel responses, each of which is…

Snapshot multi-dimensional imaging offers a promising alternative to traditional low-dimensional imaging techniques by enabling the simultaneous capture of spatial, spectral, polarization, and other information in a single shot for improved…

Deep Image Prior (DIP) has recently emerged as a promising one-shot neural-network based image reconstruction method. However, DIP has seen limited application to 3D image reconstruction problems. In this work, we introduce Tada-DIP, a…

A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we…

Imaging through opaque, highly scattering walls is a long sought after capability with potential applications in a variety of fields. The use of wavefront shaping to compensate for scattering has brought a renewed interest as a potential…

Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…

Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing maximum-a-posteriori (MAP) or posterior…

Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance on image generation tasks, enabling highly-flexible control…

In recent years, numerous vision and learning tasks have been (re)formulated as nonconvex and nonsmooth programmings(NNPs). Although some algorithms have been proposed for particular problems, designing fast and flexible optimization…

Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…