Estimating a dense depth map from a single view is geometrically ill-posed, and state-of-the-art methods rely on learning depth's relation with visual appearance using deep neural networks.
Mobile robots extract information from its environment to understand their current situation to enable intelligent decision making and autonomous task execution.
no code implementations • 29 Apr 2022 • Pablo Azagra, Carlos Sostres, Ángel Ferrandez, Luis Riazuelo, Clara Tomasini, Oscar León Barbed, Javier Morlana, David Recasens, Victor M. Batlle, Juan J. Gómez-Rodríguez, Richard Elvira, Julia López, Cristina Oriol, Javier Civera, Juan D. Tardós, Ana Cristina Murillo, Angel Lanas, José M. M. Montiel
Computer-assisted systems are becoming broadly used in medicine.
Mobile robots should be aware of their situation, comprising the deep understanding of their surrounding environment along with the estimation of its own state, to successfully make intelligent decisions and execute tasks autonomously in real environments.
Place recognition and visual localization are particularly challenging in wide baseline configurations.
In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups.
In this paper we propose a method that estimates the $SE(3)$ continuous trajectories (orientation and translation) of the dynamic rigid objects present in a scene, from multiple RGB-D views.
Estimating depth information from endoscopic images is a prerequisite for a wide set of AI-assisted technologies, such as accurate localization and measurement of tumors, or identification of non-inspected areas.
In this paper, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles.
Estimating a scene reconstruction and the camera motion from in-body videos is challenging due to several factors, e. g. the deformation of in-body cavities or the lack of texture.
Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem.
In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments.
The two topics are closely related, as the former aims to track the incremental camera motion with respect to a local map of the scene, and the latter to jointly estimate the camera trajectory and the global map with consistency.
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model.
The problem of 3D layout recovery in indoor scenes has been a core research topic for over a decade.
First we pre-process and propose a partition for the Nordland dataset, frequently used for place recognition research without consensus on the partitions.
We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods.
And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.
Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics.