Related papers: GDoeSII: Open source software for design of diffra…
In digital holography, the coherent scattered light fields can be reconstructed volumetrically. By refocusing the fields to the sample planes, absorption and phase-shift profiles of sparsely distributed samples can be simultaneously…
Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochastic differential equations (SDEs) and their…
We present the RAW domain diffusion model (RDDM), an end-to-end diffusion model that restores photo-realistic images directly from the sensor RAW data. While recent sRGB-domain diffusion methods achieve impressive results, they are caught…
We demonstrate that in situ coherent diffractive imaging (CDI), which harnesses the coherent interference between a strong and a weak beam illuminating a static and dynamic structure, can be a very dose-efficient imaging method. At low…
Accurate Speed-of-Sound (SoS) reconstruction from acoustic waveforms is a cornerstone of ultrasound computed tomography (USCT), enabling quantitative velocity mapping that reveals subtle anatomical details and pathological variations often…
Score-based diffusion models are a recently developed framework for posterior sampling in Bayesian inverse problems with a state-of-the-art performance for severely ill-posed problems by leveraging a powerful prior distribution learned from…
Broadband laser ultrasonics and two dimensional Fourier transformation are used to characterize the properties of varieties of foils and plates. Laser ultrasonics generation is achieved by use of a pulsed laser which deposits pulsed laser…
Minimally invasive surgery (MIS) requires high-fidelity, real-time visual feedback of dynamic and low-texture surgical scenes. To address these requirements, we introduce FeatureEndo-4DGS (FE-4DGS), the first real time pipeline leveraging…
Score-based diffusion models learn to reverse a stochastic differential equation that maps data to noise. However, for complex tasks, numerical error can compound and result in highly unnatural samples. Previous work mitigates this drift…
There is a need to accurately simulate materials with complex electromagnetic properties when modelling Ground Penetrating Radar (GPR), as many objects encountered with GPR contain water, e.g. soils, curing concrete, and water-filled pipes.…
Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…
Fourier ptychography microscopy (FPM), sharing its roots with synthetic aperture technique and phase retrieval method, is a recently developed computational microscopic super-resolution technique. By turning on the light-emitting diode…
Diffusion models have emerged as an expressive family of generative models rivaling GANs in sample quality and autoregressive models in likelihood scores. Standard diffusion models typically require hundreds of forward passes through the…
The spectroscopic studies of near infrared emission arising from supernovae allow to derive crucial quantities that could better characterise physical conditions of the expanding gas, such as the CaII IR HVF spectral feature. For this…
Investigating metal organic systems with time-resolved photocrystallography poses a unique challenge while interpreting the time dependent photodifference maps. In these difference Fourier maps, the signals correspond to the movement of…
Computational optical imaging (COI) systems have enabled the acquisition of high-dimensional signals through optical coding elements (OCEs). OCEs encode the high-dimensional signal in one or more snapshots, which are subsequently decoded…
Phase retrieval, or the process of recovering phase information in reciprocal space to reconstruct images from measured intensity alone, is the underlying basis to a variety of imaging applications including coherent diffraction imaging…
Metasurfaces are ultra-thin optical elements composed of engineered sub-wavelength structures that enable precise control of light. Their inverse design - determining a geometry that yields a desired optical response - is challenging due to…
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However, they often require a larger number of neural function…
Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high…