Related papers: GDoeSII: Open source software for design of diffra…
We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a…
To lower the barrier to diffractive optical neural networks (DONNs) design, exploration, and deployment, we propose LightRidge, the first end-to-end optical ML compilation framework, which consists of (1) precise and differentiable optical…
We develop a fast and scalable computational framework to solve large-scale and high-dimensional Bayesian optimal experimental design problems. In particular, we consider the problem of optimal observation sensor placement for Bayesian…
We present a novel learning-based method to build a differentiable computational model of a real fluorescence microscope. Our model can be used to calibrate a real optical setup directly from data samples and to engineer point spread…
We experimentally demonstrate a very large dynamic optical reflection modulation from a simple unpatterned layered stack of phase-change materials ultrathin films. Specifically, we theoretically and experimentally demonstrate that properly…
Deep learning (DL) has successfully automated dose distribution prediction in radiotherapy planning, enhancing both efficiency and quality. However, existing methods suffer from the over-smoothing problem for their commonly used L1 or L2…
This article presents GRFsaw, an open-source software for generating two-phase (binary) microstructures with user-defined structural properties. Unlike most standard software for microstructure generation, GRFsaw is based on the concept of…
Recently, diffusion models have shown remarkable results in image synthesis by gradually removing noise and amplifying signals. Although the simple generative process surprisingly works well, is this the best way to generate image data? For…
Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…
Bessel beams (BBs) appear immune to diffraction over finite propagation distances due to the conical nature of light propagation along the optical axis. This offers promising advantages in laser fabrication. However, BBs exhibit a…
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…
Open-source pre-trained models hold great potential for diverse applications, but their utility declines when their training data is unavailable. Data-Free Image Synthesis (DFIS) aims to generate images that approximate the learned data…
SUePDF is a graphic-user-interface program written in MATLAB to achieve quantitative pair distribution functions (PDF) from electron diffraction data. The program facilitates the structural studies of amorphous materials and small…
Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…
Imaging depth and spectrum have been extensively studied in isolation from each other for decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both information simultaneously by combining two different imaging systems;…
A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward…
The rapid evolution of the electronics industry, driven by Moore's law and the proliferation of integrated circuits, has led to significant advancements in modern society, including the Internet, wireless communication, and artificial…
With the recent proliferation of heterogeneous, GPU-accelerated supercomputers, high-order computational fluid dynamics (CFD) simulations of complex, turbulent flows are more accessible than ever. To leverage the computing power of these…
Diffusion bridge models have demonstrated promising performance in conditional image generation tasks, such as image restoration and translation, by initializing the generative process from corrupted images instead of pure Gaussian noise.…
Commercial RGB-D cameras often produce noisy, incomplete depth maps for non-Lambertian objects. Traditional depth completion methods struggle to generalize due to the limited diversity and scale of training data. Recent advances exploit…