Related papers: Depth-Based Object Tracking Using a Robust Gaussia…
Accurate detection of the centerline of a thick linear structure and good estimation of its thickness are challenging topics in many real-world applications such X-ray imaging, remote sensing and lane marking detection in road traffic.…
Using Bayesian transfer learning, we develop a particle filter approach for tracking a nonlinear dynamical model in a dual-tracking system where intensities of measurement noise for both sensors are asymmetric. The densities for Bayesian…
Most of existing correlation filter-based tracking approaches only estimate simple axis-aligned bounding boxes, and very few of them is capable of recovering the underlying similarity transformation. To tackle this challenging problem, in…
3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we propose GP-GS, a Gaussian Process (GP) based densification…
One image processing application that is very helpful for humans is to improve image quality, poor image quality makes the image more difficult to interpret because the information conveyed by the image is reduced. In the process of the…
Recently, 3D Gaussian Splatting (3D-GS) has prevailed in novel view synthesis, achieving high fidelity and efficiency. However, it often struggles to capture rich details and complete geometry. Our analysis reveals that the 3D-GS…
We present the first application of 3D Gaussian Splatting in monocular SLAM, the most fundamental but the hardest setup for Visual SLAM. Our method, which runs live at 3fps, utilises Gaussians as the only 3D representation, unifying the…
Generalized feed-forward Gaussian models have achieved significant progress in sparse-view 3D reconstruction by leveraging prior knowledge from large multi-view datasets. However, these models often struggle to represent high-frequency…
Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard current methods rely on algorithmic approaches: by fine-tuning…
Transparent object manipulation remains a significant challenge in robotics due to the difficulty of acquiring accurate and dense depth measurements. Conventional depth sensors often fail with transparent objects, resulting in incomplete or…
Object detection is a famous branch of research in computer vision, many state of the art object detection algorithms have been introduced in the recent past, but how good are those object detectors when it comes to dense object detection?…
Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation. However, existing approaches typically rely on accurate depth information, which is non-trivial to obtain in real-world…
Point clouds produced by 3D sensors are often sparse and noisy, posing challenges for tasks requiring dense and high-fidelity 3D representations. Prior work has explored both implicit feature-based upsampling and distance-function learning…
Scene reconstruction has emerged as a central challenge in computer vision, with approaches such as Neural Radiance Fields (NeRF) and Gaussian Splatting achieving remarkable progress. While Gaussian Splatting demonstrates strong performance…
We consider estimation of a deterministic unknown parameter vector in a linear model with non-Gaussian noise. In the Gaussian case, dimensionality reduction via a linear matched filter provides a simple low dimensional sufficient statistic…
This paper is centered around the approximation of dynamical systems by means of Gaussian processes. To this end, trajectories of such systems must be collected to be used as training data. The measurements of these trajectories are…
This paper presents a new Bayesian model and associated algorithm for depth and intensity profiling using full waveforms from time-correlated single-photon counting (TCSPC) measurements in the limit of very low photon counts (i.e.,…
Most Kalman filter extensions assume Gaussian noise and when the noise is non-Gaussian, usually other types of filters are used. These filters, such as particle filter variants, are computationally more demanding than Kalman type filters.…
Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…
Deformable Image Registration (DIR) is essential for aligning medical images that exhibit anatomical variations, facilitating applications such as disease tracking and radiotherapy planning. While classical iterative methods and deep…