Zobrazeno 1 - 10
of 102
pro vyhledávání: '"P. Hornauer"'
Metric depth prediction from monocular videos suffers from bad generalization between datasets and requires supervised depth data for scale-correct training. Self-supervised training using multi-view reconstruction can benefit from large scale natura
Externí odkaz:
http://arxiv.org/abs/2412.01637
Sound plays a major role in human perception. Along with vision, it provides essential information for understanding our surroundings. Despite advances in neural implicit representations, learning acoustics that align with visual scenes remains a cha
Externí odkaz:
http://arxiv.org/abs/2405.18213
In monocular depth estimation, unsupervised domain adaptation has recently been explored to relax the dependence on large annotated image-based depth datasets. However, this comes at the cost of training multiple models or requiring complex training
Externí odkaz:
http://arxiv.org/abs/2405.17704
Autor:
Chekroun, Raphael, Wang, Han, Lee, Jonathan, Toromanoff, Marin, Hornauer, Sascha, Moutarde, Fabien, Monache, Maria Laura Delle
Accurate real-time traffic state forecasting plays a pivotal role in traffic control research. In particular, the CIRCLES consortium project necessitates predictive techniques to mitigate the impact of data source delays. After the success of the Meg
Externí odkaz:
http://arxiv.org/abs/2402.05663
We present MBAPPE, a novel approach to motion planning for autonomous driving combining tree search with a partially-learned model of the environment. Leveraging the inherent explainable exploration and optimization capabilities of the Monte-Carlo Se
Externí odkaz:
http://arxiv.org/abs/2309.08452
In monocular depth estimation, uncertainty estimation approaches mainly target the data uncertainty introduced by image noise. In contrast to prior work, we address the uncertainty due to lack of knowledge, which is relevant for the detection of data
Externí odkaz:
http://arxiv.org/abs/2308.06072
Publikováno v:
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Vision research showed remarkable success in understanding our world, propelled by datasets of images and videos. Sensor data from radar, LiDAR and cameras supports research in robotics and autonomous driving for at least a decade. However, while vis
Externí odkaz:
http://arxiv.org/abs/2303.07257
Our work investigates out-of-distribution (OOD) detection as a neural network output explanation problem. We learn a heatmap representation for detecting OOD images while visualizing in- and out-of-distribution image regions at the same time. Given a
Externí odkaz:
http://arxiv.org/abs/2211.08115
In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous predictions. For that reason, uncertainty estimates for each pixel are necessary, in particular for safety-cri
Externí odkaz:
http://arxiv.org/abs/2208.02005
Deep reinforcement learning (DRL) has been demonstrated to be effective for several complex decision-making applications such as autonomous driving and robotics. However, DRL is notoriously limited by its high sample complexity and its lack of stabil
Externí odkaz:
http://arxiv.org/abs/2111.08575