相关论文: Fully-Automatic Multiresolution Idealization for F…

Occlusion and clutter are two scene states that make it difficult to detect anomalies in surveillance video. Furthermore, anomaly events are rare and, as a consequence, class imbalance and lack of labeled anomaly data are also key features…

High-speed imaging is central to the experimental investigation of fast phenomena, like flapping flags. Event-based cameras use new types of sensors that address typical challenges such as low illumination conditions, large data transfer,…

It has been shown that a flux--weighted full width at half maximum timescale of a microlensing event can be used in an unbiased estimator of the optical depth. For the first time, this allows a physical parameter to be easily estimated from…

Event cameras are bio-inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has…

In a focused ion beam (FIB) microscope, source particles interact with a small volume of a sample to generate secondary electrons that are detected, pixel by pixel, to produce a micrograph. Randomness of the number of incident particles…

Event-based cameras, also known as neuromorphic cameras, are bioinspired sensors able to perceive changes in the scene at high frequency with low power consumption. Becoming available only very recently, a limited amount of work addresses…

Implicit neural representation and explicit 3D Gaussian Splatting (3D-GS) for novel view synthesis have achieved remarkable progress with frame-based camera (e.g. RGB and RGB-D cameras) recently. Compared to frame-based camera, a novel type…

In this paper, we propose a recurrent framework for Joint Unsupervised LEarning (JULE) of deep representations and image clusters. In our framework, successive operations in a clustering algorithm are expressed as steps in a recurrent…

In this work, we address in-context learning (ICL) for the task of image segmentation, introducing a novel approach that adapts a modern Video Object Segmentation (VOS) technique for visual in-context learning. This adaptation is inspired…

Segmentation of moving objects in dynamic scenes is a key process in scene understanding for navigation tasks. Classical cameras suffer from motion blur in such scenarios rendering them effete. On the contrary, event cameras, because of…

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a convolutional network with context-aware skip connections, and compressed, hypercolumn image features combined with a…

Molecular dynamics is a versatile and powerful method to study diffusion in solid-state ionic conductors, requiring minimal prior knowledge of equilibrium or transition states of the system's free energy surface. However, the analysis of…

Separating moving and static objects from a moving camera viewpoint is essential for 3D reconstruction, autonomous navigation, and scene understanding in robotics. Existing approaches often rely primarily on optical flow, which struggles to…

Convolution and cross-correlation are the basis of filtering and pattern or template matching in multimedia signal processing. We propose two throughput scaling options for any one-dimensional convolution kernel in programmable processors…

Detection of circular objects in digital images is an important problem in several vision applications. Circle detection using randomized sampling has been developed in recent years to reduce the computational intensity. Randomized…

Removing speckle noise from medical ultrasound images while preserving image features without introducing artifact and distortion is a major challenge in ultrasound image restoration. In this paper, we propose a multiframe-based adaptive…

Due to their high temporal resolution and large dynamic range, event cameras are uniquely suited for the analysis of time-periodic signals in an image. In this work we present an efficient and fully asynchronous event camera algorithm for…

Deconvolution is the important problem of estimating the distribution of a quantity of interest from a sample with additive measurement error. Nearly all methods in the literature are based on Fourier transformation because it is…

Pixel intensity is a widely used feature for clustering and segmentation algorithms, the resulting segmentation using only intensity values might suffer from noises and lack of spatial context information. Wavelet transform is often used…

In this paper, we establish a new scheme for identification and classification of high intensity events generated by the propagation of light through a photorefractive SBN crystal. Among these events, which are the inevitable consequence of…