no code implementations • 21 Feb 2024 • Gianluca Monaci, Leonid Antsfeld, Boris Chidlovskii, Christian Wolf
Bird's-eye view (BEV) maps are an important geometrically structured representation widely used in robotics, in particular self-driving vehicles and terrestrial robots.
no code implementations • 25 Jan 2024 • Guillaume Bono, Hervé Poirier, Leonid Antsfeld, Gianluca Monaci, Boris Chidlovskii, Christian Wolf
In the context of autonomous navigation of terrestrial robots, the creation of realistic models for agent dynamics and sensing is a widespread habit in the robotics literature and in commercial applications, where they are used for model based control and/or for localization and mapping.
no code implementations • 24 Jan 2024 • Assem Sadek, Guillaume Bono, Boris Chidlovskii, Atilla Baskurt, Christian Wolf
More recently, beyond waypoint planning, problems involving significant components of (visual) high-level reasoning have been explored in simulated environments, mostly addressed with large-scale machine learning, in particular RL, offline-RL or imitation learning.
1 code implementation • 21 Dec 2023 • Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jerome Revaud
Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera.
no code implementations • 28 Sep 2023 • Guillaume Bono, Leonid Antsfeld, Boris Chidlovskii, Philippe Weinzaepfel, Christian Wolf
The main challenge lies in learning compact representations generalizable to unseen environments and in learning high-capacity perception modules capable of reasoning on high-dimensional input.
no code implementations • 13 Feb 2023 • Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.
1 code implementation • ICCV 2023 • Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon, Vaibhav Arora, Romain Brégier, Gabriela Csurka, Leonid Antsfeld, Boris Chidlovskii, Jérôme Revaud
Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow.
Ranked #1 on Optical Flow Estimation on KITTI 2012
1 code implementation • 19 Oct 2022 • Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas, Romain Brégier, Yohann Cabon, Vaibhav Arora, Leonid Antsfeld, Boris Chidlovskii, Gabriela Csurka, Jérôme Revaud
More precisely, we propose the pretext task of cross-view completion where the first input image is partially masked, and this masked content has to be reconstructed from the visible content and the second image.
1 code implementation • CVPR 2022 • Jérome Revaud, Vincent Leroy, Philippe Weinzaepfel, Boris Chidlovskii
In this paper, we propose to explicitly integrate two matching priors in a single loss in order to learn local descriptors without supervision.
no code implementations • 6 Dec 2021 • Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.
no code implementations • 29 Nov 2021 • Assem Sadek, Guillaume Bono, Boris Chidlovskii, Christian Wolf
In this work we present an in-depth study of the performance and reasoning capacities of real physical agents, trained in simulation and deployed to two different physical environments.
no code implementations • 26 Aug 2021 • Leonid Antsfeld, Boris Chidlovskii
For the first setup, we revise the state of the art approaches and propose a novel extended pipeline to benefit from the presence of magnetic anomalies in indoor environment created by different ferromagnetic objects.
no code implementations • 25 Aug 2021 • Shyamgopal Karthik, Jérome Revaud, Boris Chidlovskii
In addition, the resulting learned representations are also remarkably robust to label noise, when fine-tuned with an imbalance- and noise-resistant loss function.
no code implementations • 22 Jun 2021 • Boris Chidlovskii, Assem Sadek, Christian Wolf
We address the problem of universal domain adaptation (UDA) in ordinal regression (OR), which attempts to solve classification problems in which labels are not independent, but follow a natural order.
no code implementations • 21 Nov 2020 • Leonid Antsfeld, Boris Chidlovskii, Emilio Sansano-Sansano
We address the indoor localization problem, where the goal is to predict user's trajectory from the data collected by their smartphone, using inertial sensors such as accelerometer, gyroscope and magnetometer, as well as other environment and network sensors such as barometer and WiFi.
no code implementations • 20 Nov 2020 • Maxime Pietrantoni, Boris Chidlovskii, Tomi Silander
The navigation pipeline is decomposed as a localization module, a planning module and a local navigation module.
no code implementations • 20 Jun 2020 • Boris Chidlovskii, Assem Sadek
We address the problem of camera pose estimation in visual localization.
no code implementations • 27 Apr 2020 • Assem Sadek, Boris Chidlovskii
We address the problem of depth and ego-motion estimation from image sequences.
no code implementations • 17 Sep 2019 • Boris Chidlovskii
We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably.
no code implementations • 17 Dec 2018 • Giorgio Giannone, Boris Chidlovskii
We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images.
no code implementations • 21 Dec 2017 • Boris Chidlovskii
We address the problem of modeling and prediction of a set of temporal events in the context of intelligent transportation systems.
no code implementations • 19 Dec 2017 • Boris Chidlovskii
In the context of public transport modeling and simulation, we address the problem of mismatch between simulated transit trips and observed ones.