Related papers: Fully-Automatic Multiresolution Idealization for F…
Robust scene segmentation and keyframe extraction are essential preprocessing steps in video understanding pipelines, supporting tasks such as indexing, summarization, and semantic retrieval. However, existing methods often lack…
Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level. Recently, two-stream approaches that leverage both RGB images and optical…
CLEAN algorithms are a class of deconvolution solvers which are widely used to remove the effect of the telescope Point Spread Function (PSF). Loop gain is one important parameter in CLEAN algorithms. Currently the parameter is fixed during…
We introduce GeMS, a framework for 3D Gaussian Splatting (3DGS) designed to handle severely motion-blurred images. State-of-the-art deblurring methods for extreme blur, such as ExBluRF, as well as Gaussian Splatting-based approaches like…
The detection and parametrization of molecular clumps is the first step in studying them. We propose a method based on Local Density Clustering algorithm while physical parameters of those clumps are measured using the Multiple Gaussian…
In regression and causal inference, controlled subgroup selection aims to identify, with inferential guarantees, a subgroup (defined as a subset of the covariate space) on which the average response or treatment effect is above a given…
Deconvolution is the most commonly used image processing method to remove the blur caused by the point-spread-function (PSF) in optical imaging systems. While this method has been successful in deblurring, it suffers from several…
Image smoothing is by reducing pixel-wise gradients to smooth out details. As existing methods always rely on gradients to determine smoothing manners, it is difficult to distinguish structures and details to handle distinctively due to the…
Object segmentation for robotic grasping under dynamic conditions often faces challenges such as occlusion, low light conditions, motion blur and object size variance. To address these challenges, we propose a Deep Learning network that…
We study a blind deconvolution problem on graphs, which arises in the context of localizing a few sources that diffuse over networks. While the observations are bilinear functions of the unknown graph filter coefficients and sparse input…
Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high…
Mirrors can degrade the performance of computer vision models, but research into detecting them is in the preliminary phase. YOLOv4 achieves phenomenal results in terms of object detection accuracy and speed, but it still fails in detecting…
Due to the choice of very dense star fields for a higher event rate, the current microlensing searches suffer from large uncertainties caused by blending effect. To measure light variations of microlensing events free from the effect of…
Event cameras are bio-inspired sensors that asynchronously report intensity changes in microsecond resolution. DAVIS can capture high dynamics of a scene and simultaneously output high temporal resolution events and low frame-rate intensity…
Radio echo sounding (RES) is a common technique used in subsurface glacial imaging, which provides insight into the underlying rock and ice. However, systematic noise is introduced into the data during collection, complicating…
Lagrangian particle tracking is essential for characterizing turbulent flows, but inferring particle acceleration from inherently noisy position data remains a significant challenge. Fluid particles in turbulence experience extreme,…
We present a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images. The proposed network is very simple and flexible with variations that gracefully trade off between speed and accuracy for…
We tackle the problem of class incremental learning (CIL) in the realm of landcover classification from optical remote sensing (RS) images in this paper. The paradigm of CIL has recently gained much prominence given the fact that data are…
Chip-based Evanescent Light Scattering (cELS) utilizes the multiple modes of a high-index contrast optical waveguide for near-field illumination of unlabeled samples, thereby repositioning the highest spatial frequencies of the sample into…
Remote sensing semantic segmentation aims to assign automatically each pixel on aerial images with specific label. In this letter, we proposed a new module, called improved-flow warp module (IFWM), to adjust semantic feature maps across…