Zobrazeno 1 - 10
of 26
pro vyhledávání: '"CHABOT, Florian"'
The Bird's-eye View (BeV) representation is widely used for 3D perception from multi-view camera images. It allows to merge features from different cameras into a common space, providing a unified representation of the 3D scene. The key component is
Externí odkaz:
http://arxiv.org/abs/2407.14108
Semi-Supervised Learning (SSL) seeks to leverage large amounts of non-annotated data along with the smallest amount possible of annotated data in order to achieve the same level of performance as if all data were annotated. A fruitful method in SSL i
Externí odkaz:
http://arxiv.org/abs/2405.14313
Autor:
Petit, Doriand, Bourgeois, Steve, Pavel, Dumitru, Gay-Bellile, Vincent, Chabot, Florian, Barthe, Loic
Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly inject generic
Externí odkaz:
http://arxiv.org/abs/2312.03357
Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfections of these approaches, a quantification of the prediction confide
Externí odkaz:
http://arxiv.org/abs/2311.06137
Recent works have shown that objects discovery can largely benefit from the inherent motion information in video data. However, these methods lack a proper background processing, resulting in an over-segmentation of the non-object regions into random
Externí odkaz:
http://arxiv.org/abs/2311.02633
Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for multiple ob
Externí odkaz:
http://arxiv.org/abs/2212.10124
We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy produces better l
Externí odkaz:
http://arxiv.org/abs/2205.15173
Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications
Externí odkaz:
http://arxiv.org/abs/2101.02471
Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to efficiently
Externí odkaz:
http://arxiv.org/abs/1911.01149
Autor:
Chabot, Florian
Les travaux développés dans cette thèse s’intéressent à l’analyse fine des véhicules à partir d’une image. Nous définissons le terme d’analyse fine comme un regroupement des concepts suivants : la détection des véhicules dans l’im
Externí odkaz:
http://www.theses.fr/2017CLFAC018/document