Related papers: Gigahertz-rate random speckle projection for high-…

Many materials have distinct spectral profiles. This facilitates estimation of the material composition of a scene at each pixel by first acquiring its hyperspectral image, and subsequently filtering it using a bank of spectral profiles.…

Ghost imaging (GI) is a potential imaging technique that reconstructs the target scene from its correlated measurements with a sequential of patterns. Restricted by the multi-shot principle, GI usually requires long acquisition time and is…

We experimentally generate speckle patterns with non-Rayleigh intensity statistics using a phase-only spatial light modulator. By introducing high order correlations to the input light fields we redistribute the intensity among the speckle…

Ghost projection is the reversed process of computational classical ghost imaging that allows any desired image to be synthesized using a linear combination of illuminating patterns. Typically, physical attenuating masks are used to produce…

Image superresolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures, typically with high…

Statistical processing of speckle data enables observation of speed of processes. In intensity-based pointwise dynamic speckle analysis, a map related to speed's spatial distribution is extracted from a sequence of speckle patterns formed…

We propose a novel spectral generative model for image synthesis that departs radically from the common variational, adversarial, and diffusion paradigms. In our approach, images, after being flattened into one-dimensional signals, are…

We describe here a method to generate high-definition arbitrary laser beam shapes and profiles useful to many applications, ranging from optical patterning and lithography to optical trapping of microscopic particles and ultracold atoms.…

Recent advancements in image restoration methods employing global modeling have shown promising results. However, these approaches often incur substantial memory requirements, particularly when processing ultra-high-definition (UHD) images.…

When imaging moving objects, single-pixel imaging produces motion blur. This paper proposes a new single-pixel imaging method, which can achieve anti-motion blur imaging of a fast-moving object. The geometric moment patterns and Hadamard…

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to…

We introduce a new spectral method for image segmentation that incorporates long range relationships for global appearance modeling. The approach combines two different graphs, one is a sparse graph that captures spatial relationships…

3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique. Previous studies often rely on publicly available datasets for…

Multi-mode fibers provide an increased amount of data transfer rates given a large number of transmission modes. Unfortunately, the increased number of modes in a multi-mode fiber hinders the accurate transfer of information due to…

We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator and discriminator…

Convolutional neural networks have been widely applied to hyperspectral image classification. However, traditional convolutions can not effectively extract features for objects with irregular distributions. Recent methods attempt to address…

Preprocessing is a well-established technique for optimizing compression, yet existing methods are predominantly Rate-Distortion (R-D) optimized and constrained by pixel-level fidelity. This work pioneers a shift towards Rate-Perception…

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

Single-pixel cameras based on the concepts of compressed sensing (CS) leverage the inherent structure of images to retrieve them with far fewer measurements and operate efficiently over a significantly broader spectral range than…