Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Postels, Janis"'
Neural Fields (NFs) have gained momentum as a tool for compressing various data modalities - e.g. images and videos. This work leverages previous advances and proposes a novel NF-based compression algorithm for 3D data. We derive two versions of our
Externí odkaz:
http://arxiv.org/abs/2311.13009
Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes limitations on data distributions that reside on lower dim
Externí odkaz:
http://arxiv.org/abs/2208.08932
Autor:
Sun, Tao, Segu, Mattia, Postels, Janis, Wang, Yuxuan, Van Gool, Luc, Schiele, Bernt, Tombari, Federico, Yu, Fisher
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, however, fall short of capturing the mutable nature of the real world. In th
Externí odkaz:
http://arxiv.org/abs/2206.08367
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing their reconstruction performance. This work investigates INRs from a no
Externí odkaz:
http://arxiv.org/abs/2112.04267
Autor:
Postels, Janis, Segu, Mattia, Sun, Tao, Sieber, Luca, Van Gool, Luc, Yu, Fisher, Tombari, Federico
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these determinis
Externí odkaz:
http://arxiv.org/abs/2107.00649
Publikováno v:
International Conference on 3D Vision 2021
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training times and la
Externí odkaz:
http://arxiv.org/abs/2106.03135
Generative models able to synthesize layouts of different kinds (e.g. documents, user interfaces or furniture arrangements) are a useful tool to aid design processes and as a first step in the generation of synthetic data, among other tasks. We explo
Externí odkaz:
http://arxiv.org/abs/2104.02416
Autor:
Postels, Janis, Blum, Hermann, Strümpler, Yannick, Cadena, Cesar, Siegwart, Roland, Van Gool, Luc, Tombari, Federico
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution moreover correlates with a model's epistemic uncertainty, thus indicat
Externí odkaz:
http://arxiv.org/abs/2012.03082
We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much o
Externí odkaz:
http://arxiv.org/abs/1908.00598
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.