Related papers: High-speed generation of vector beams through rand…
This paper introduces a fast algorithm for randomized computation of a low-rank Dynamic Mode Decomposition (DMD) of a matrix. Here we consider this matrix to represent the development of a spatial grid through time e.g. data from a static…
Deep image generation is becoming a tool to enhance artists and designers creativity potential. In this paper, we aim at making the generation process more structured and easier to interact with. Inspired by vector graphics systems, we…
We report a demonstration video-rate heterodyne holography in off-axis configuration. Reconstruction and display of 1 Megapixel holograms is achieved at 24 frames per second, with a graphics processing unit. Our claims are validated with…
Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful…
Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired…
This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…
Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality and complex temporal dynamics along with large spatial…
High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR…
Holographic techniques significantly extend the capabilities of laser tweezing, making possible extended trapping patterns for manipulating large numbers of particles and volumes of soft matter. We describe practical methods for creating…
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which significantly differ from the text generation methods employed by…
We report that guiding light beams, ranging from continuous beams to femtosecond pulses, along liquid crystal defect lines can transform them into vector beams with various polarization profiles. Using Finite Difference Time Domain…
Beam halo is an important factor in any high intensity accelerator. It can cause difficulties in the control of the beam, emittance growth, particle loss and even damage to the accelerator. It is therefore essential to understand the…
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…
Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…
Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues, diversity limitations in generative models are hard to detect visually, requiring…
A head-mounted display (HMD) using holography technology (holo-HMD) is expected to be the next generation of HMDs capable of reducing three-dimensional sickness. In HMDs, it is important to generate images that respond to head movement in…
Ultrathin metasurface holograms, with thicknesses comparable to the operating wavelength, leverage multiple degrees of freedom of light to address independent image channels, thereby significantly enhancing information capacity. Although…
Exclusive production of light vector mesons in deep inelastic scattering is calculated at next-to-leading order in the dipole picture in the limit of high photon virtuality. The resulting expression is free of any divergences and suitable…
In this paper we implement experimentally the spatial shape modelling of nondiffracting optical beams via computer generated holograms. The results reported here are the experimental confirmation of the so called Frozen Wave method,…
Prior methods for controlling image generation are limited in their ability to be taught new tasks. In contrast, vision-language models, or VLMs, can learn tasks in-context and produce the correct outputs for a given input. We propose a…