Related papers: Quantitative and Qualitative Study of Gaussian Bea…
The expressive power of Bayesian kernel-based methods has led them to become an important tool across many different facets of artificial intelligence, and useful to a plethora of modern application domains, providing both power and…
We introduce a novel edge tracing algorithm using Gaussian process regression. Our edge-based segmentation algorithm models an edge of interest using Gaussian process regression and iteratively searches the image for edge pixels in a…
The widespread use of image acquisition technologies, along with advances in facial recognition, has raised serious privacy concerns. Face de-identification usually refers to the process of concealing or replacing personal identifiers,…
The use of a wire probe is a robust method for beam profile measurement, but it can only provide a 1D projection of the beam profile. In this study, we developed a novel method for measuring a beam projected from a 360{\deg} angle by a…
Gaussian graphical models are widely used to infer dependence structures. Bayesian methods are appealing to quantify uncertainty associated with structural learning, i.e., the plausibility of conditional independence statements given the…
With the democratization of 3D LiDAR sensors, precise LiDAR odometries and SLAM are in high demand. New methods regularly appear, proposing solutions ranging from small variations in classical algorithms to radically new paradigms based on…
The pencil-beam model is valid only when elementary Gaussian beams are small enough with respect to lateral heterogeneity of a medium, which is not always the case in heavy charged particle radiotherapy. This work addresses a solution for…
We previously demonstrated near-field speckle scanning based x-ray imaging to be an easy-to-implement phase sensing method capable of providing both high sensitivity and high resolution. Yet, this performance combination could only be…
Gaussian Splatting (GS) has proven to be highly effective in novel view synthesis, achieving high-quality and real-time rendering. However, its potential for reconstructing detailed 3D shapes has not been fully explored. Existing methods…
Continuous-time trajectory estimation is an attractive alternative to discrete-time batch estimation due to the ability to incorporate high-frequency measurements from asynchronous sensors while keeping the number of optimization parameters…
Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging…
Fast, reliable shape reconstruction is an essential ingredient in many computer vision applications. Neural Radiance Fields demonstrated that photorealistic novel view synthesis is within reach, but was gated by performance requirements for…
Gaussian Splatting has recently emerged as the go-to representation for reconstructing and rendering 3D scenes. The transition from 3D to 2D Gaussian primitives has further improved multi-view consistency and surface reconstruction…
Rapid diagnosis of gastric cancer is a great challenge for clinical doctors. Dramatic progress of computer vision on gastric cancer has been made recently and this review focuses on advances during the past five years. Different methods for…
The characterization of a third order nonlinear integrated waveguide is reported for the first time by means of a top-hat Dispersive-Scan (D-Scan) technique, a temporal analog of the top-hat Z-Scan. With a single laser beam, and by carrying…
In medical image visualization, path tracing of volumetric medical data like CT scans produces lifelike three-dimensional visualizations. Immersive VR displays can further enhance the understanding of complex anatomies. Going beyond the…
We investigate adaptive design based on a single sparse pilot scan for generating effective scanning strategies for computed tomography reconstruction. We propose a novel approach using the linearised deep image prior. It allows…
Line spectral estimation (LSE) from multi snapshot samples is studied utilizing the variational Bayesian methods. Motivated by the recently proposed variational line spectral estimation (VALSE) method for a single snapshot, we develop the…
We present a detailed study of the gaussian laser propagation through a dielectric system composed by two right angle prisms. We investigate the transition between the spatial coherence limit, which exhibits wave-like properties and for…
3D scene stylization extends the work of neural style transfer to 3D. A vital challenge in this problem is to maintain the uniformity of the stylized appearance across multiple views. A vast majority of the previous works achieve this by…