Related papers: Toward Geometric Deep SLAM
Traditional attempts for loop closure detection typically use hand-crafted features, relying on geometric and visual information only, whereas more modern approaches tend to use semantic, appearance or geometric features extracted from deep…
The choice of scene representation is crucial in both the shape inference algorithms it requires and the smart applications it enables. We present efficient and optimisable multi-class learned object descriptors together with a novel…
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…
The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage. Current popular trackers…
We introduce a novel CNN-based feature point detector - GLAMpoints - learned in a semi-supervised manner. Our detector extracts repeatable, stable interest points with a dense coverage, specifically designed to maximize the correct matching…
Recently neural radiance fields (NeRF) have been widely exploited as 3D representations for dense simultaneous localization and mapping (SLAM). Despite their notable successes in surface modeling and novel view synthesis, existing…
We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The…
Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely disjoint approaches towards building a 3D map of the…
Visual SLAM algorithms achieve significant improvements through the exploration of 3D Gaussian Splatting (3DGS) representations, particularly in generating high-fidelity dense maps. However, they depend on a static environment assumption…
We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion and monocular SLAM techniques assume input…
In dynamic environments, performance of visual SLAM techniques can be impaired by visual features taken from moving objects. One solution is to identify those objects so that their visual features can be removed for localization and…
Conventional SLAM techniques strongly rely on scene rigidity to solve data association, ignoring dynamic parts of the scene. In this work we present Semi-Direct DefSLAM (SD-DefSLAM), a novel monocular deformable SLAM method able to map…
A dense SLAM system is essential for mobile robots, as it provides localization and allows navigation, path planning, obstacle avoidance, and decision-making in unstructured environments. Due to increasing computational demands the use of…
Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots. However, existing SLAM (Simultaneous Localization…
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between…
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a…
Existing Simultaneous Localization and Mapping (SLAM) approaches are limited in their scalability due to growing map size in long-term robot operation. Moreover, processing such maps for localization and planning tasks leads to the…
Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…
The simultaneous localization and mapping (SLAM) problem is considered in three dimensions. The proposed algorithm, differential geometric SLAM (DG-SLAM), employs methods from differential geometry to propagate the state and map estimates.…
We propose DeepMapping, a novel registration framework using deep neural networks (DNNs) as auxiliary functions to align multiple point clouds from scratch to a globally consistent frame. We use DNNs to model the highly non-convex mapping…