Related papers: A Structurally Coherent Spatial Phase Estimate
Topological data analysis offers a rich source of valuable information to study vision problems. Yet, so far we lack a theoretically sound connection to popular kernel-based learning techniques, such as kernel SVMs or kernel PCA. In this…
VINGS-Mono is a monocular (inertial) Gaussian Splatting (GS) SLAM framework designed for large scenes. The framework comprises four main components: VIO Front End, 2D Gaussian Map, NVS Loop Closure, and Dynamic Eraser. In the VIO Front End,…
In synthetic aperture radar (SAR) image change detection, it is quite challenging to exploit the changing information from the noisy difference image subject to the speckle. In this paper, we propose a multi-scale spatial pooling (MSSP)…
Convolutional Neural Networks (ConvNets) at present achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of the mammalian visual systems such as invariance to contrast and…
The Coherent Multiplex is formalized and validated as a scalable, real-time system for identifying, analyzing, and visualizing coherence among multiple time series. Its architecture comprises a fast spectral similarity layer based on cosine…
Temporal patterns of cardiac motion provide important information for cardiac disease diagnosis. This pattern could be obtained by three-directional CINE multi-slice left ventricular myocardial velocity mapping (3Dir MVM), which is a…
Singular beams have attracted great attention due to their optical properties and broad applications from light manipulation to optical communications. However, there has been a lack of practical schemes with which to achieve switchable…
Understanding microstructure-property relationships (MPRs) is essential for optimising the performance of multiphase composites. Image-based poro/micro-mechanical modelling provides a non-invasive approach to exploring MPRs, but the…
Time multiplexed approaches for high frame-rate holographic displays have been around since the invention of One-Step Phase-Retrieval (OSPR) in the early 2000s. When discovered, formulations were created for variance reduction but other…
A photonics-assisted joint communication-radar system is proposed and experimentally demonstrated, by introducing a quadrature phase-shift keying (QPSK)-sliced linearly frequency-modulated (LFM) signal. An LFM signal is carrier-suppressed…
In recent decades, biomedical signals have been used for communication in Human-Computer Interfaces (HCI) for medical applications; an instance of these signals are the myoelectric signals (MES), which are generated in the muscles of the…
We propose a fast and generalizable solution to Multi-view Photometric Stereo (MVPS), called MVPSNet. The key to our approach is a feature extraction network that effectively combines images from the same view captured under multiple…
We propose a deep multitask architecture for \emph{fully automatic 2d and 3d human sensing} (DMHS), including \emph{recognition and reconstruction}, in \emph{monocular images}. The system computes the figure-ground segmentation,…
Delay-and-Sum (DAS) is the most common algorithm used in photoacoustic (PA) image formation. However, this algorithm results in a reconstructed image with a wide mainlobe and high level of sidelobes. Minimum variance (MV), as an adaptive…
Edge detection remains a fundamental yet challenging task in computer vision, especially under varying illumination, noise, and complex scene conditions. This paper introduces a Hybrid Multi-Stage Learning Framework that integrates…
Depth estimation and semantic segmentation play essential roles in scene understanding. The state-of-the-art methods employ multi-task learning to simultaneously learn models for these two tasks at the pixel-wise level. They usually focus…
Until quite recently, the backbone of nearly every state-of-the-art computer vision model has been the 2D convolution. At its core, a 2D convolution simultaneously mixes information across both the spatial and channel dimensions of a…
In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often ignore semantic features, leading to detail loss and ground…
High-fidelity compression of multispectral solar imagery remains challenging for space missions, where limited bandwidth must be balanced against preserving fine spectral and spatial details. We present a learned image compression framework…
Visual prompting has recently emerged as an efficient strategy to adapt vision models using lightweight, learnable parameters injected into the input space. However, prior work mainly targets large Vision Transformers and high-resolution…