no code implementations • 18 Sep 2023 • Mathieu Cocheteux, Julien Moreau, Franck Davoine
Camera-LiDAR extrinsic calibration is a critical task for multi-sensor fusion in autonomous systems, such as self-driving vehicles and mobile robots.
no code implementations • 28 Feb 2023 • Vincent Brebion, Julien Moreau, Franck Davoine
In this work, we propose to address these issues by fusing information from an event camera and a LiDAR using a learning-based approach to estimate accurate dense depth maps.
no code implementations • 12 Dec 2022 • Maxime Chaveroche, Franck Davoine, Véronique Cherfaoui
In particular, we propose Locally Predictable VAE (LP-VAE), which appears to be producing better belief states for predictions than state-of-the-art models, both as a standalone model and in the context of DRL.
1 code implementation • 20 Dec 2021 • Vincent Brebion, Julien Moreau, Franck Davoine
As an answer to these points, we propose an optimized framework for computing optical flow in real-time with both low- and high-resolution event cameras.
1 code implementation • 12 Oct 2021 • Fei Yang, Franck Davoine, Huan Wang, Zhong Jin
Furthermore, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation.
no code implementations • 13 Jul 2021 • Maxime Chaveroche, Franck Davoine, Véronique Cherfaoui
With it, we are able to reduce these computations up to a linear complexity in the number of focal sets in some cases.
no code implementations • 5 Feb 2021 • Edouard Capellier, Franck Davoine, Veronique Cherfaoui, You Li
So as to reach satisfactory results, the system fuses road detection results obtained from three variants of RoadSeg, processing different LIDAR features.
1 code implementation • 12 Nov 2020 • Maxime Chaveroche, Franck Davoine, Véronique Cherfaoui
Dempster-Shafer Theory (DST) generalizes Bayesian probability theory, offering useful additional information, but suffers from a much higher computational burden.
3 code implementations • ICML 2018 • Xuhong Li, Yves GRANDVALET, Franck Davoine
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch.
no code implementations • ICLR 2018 • Xuhong LI, Yves GRANDVALET, Franck Davoine
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch.