Bayesian deep learning for affordance segmentation in images

L Mur-Labadia, R Martinez-Cantin… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Affordances are a fundamental concept in robotics since they relate available actions for an
agent depending on its sensory-motor capabilities and the environment. We present a novel …

Introspective perception for mobile robots

S Rabiee, J Biswas - Artificial Intelligence, 2023 - Elsevier
Perception algorithms that provide estimates of their uncertainty are crucial to the
development of autonomous robots that can operate in challenging and uncontrolled …

On the uncertain single-view depths in colonoscopies

J Rodriguez-Puigvert, D Recasens, J Civera… - … Conference on Medical …, 2022 - Springer
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 …

LightDepth: Single-View Depth Self-Supervision from Illumination Decline

J Rodríguez-Puigvert, VM Batlle… - Proceedings of the …, 2023 - openaccess.thecvf.com
Single-view depth estimation can be remarkably effective if there is enough ground-truth
depth data for supervised training. However, there are scenarios, especially in medicine in …

LightDepth: Single-View Depth Self-Supervision from Illumination Decline

J Puigvert, V Batlle, J Montiel, R Cantin… - … on Computer Vision …, 2023 - infoscience.epfl.ch
Résumé Single-view depth estimation can be remarkably effective if there is enough ground-
truth depth data for supervised training. However, there are scenarios, especially in …

ProbNet: Bayesian deep neural network for point cloud analysis

X Wang, K Zhang, H Li, H Luo, J Wang - Computers & Graphics, 2022 - Elsevier
Deep neural networks exhibit extreme superiority in natural language processing and
computer vision. With the fast development of 3D sensing technology, point cloud has been …

Uncertainty and Self-Supervision in Single-View Depth

J Rodriguez-Puigvert - arxiv preprint arxiv:2406.14226, 2024 - arxiv.org
Single-view depth estimation refers to the ability to derive three-dimensional information per
pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed …

On Performance and Calibration of Natural Gradient Langevin Dynamics

HA Robbani, A Bustamam, R Adnan, S Ahmad - IEEE Access, 2023 - ieeexplore.ieee.org
Producing deep neural network (DNN) models with calibrated confidence is essential for
applications in many fields, such as medical image analysis, natural language processing …

Model-Based Policy Optimization for Legged Locomotion

J Garcia-Barcos, R Martinez-Cantin… - 2024 7th Iberian …, 2024 - ieeexplore.ieee.org
In this paper, we explore model-based reinforcement learning (MBRL) for legged locomotion
in robotics, employing state-of-the-art techniques to evaluate the performance and stability of …

Analysis of linearization methods for Bayesian Deep Learning.

C Plou Izquierdo, R Martínez Cantín, AC Murillo Arnal - zaguan.unizar.es
Deep learning has revolutionized the field of machine learning, outperforming traditional
methods in a wide range of areas such as computer vision, robotics or natural language …