13 citations · 21 across the 12 of their papers we have counts for
14 papers
VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining
Marwane Hariat, David Filliat, Antoine Manzanera
Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signal…
Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models
Marwane Hariat, Gianni Franchi, David Filliat +1
We present Casper3D, a lightweight probabilistic framework for converting noisy multi-view 2D foundation-model embeddings into a latent 3D semantic representation. We model view-le…
SS3D: End2End Self-Supervised 3D from Web Videos
Marwane Hariat, Gianni Franchi, David Filliat +1
We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and…
Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks
Marwane Hariat, Antoine Manzanera, David Filliat
Monocular depth estimation (MDE) with self-supervised training approaches struggles in low-texture areas, where photometric losses may lead to ambiguous depth predictions. To addre…
Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions
Marwane Hariat, Antoine Manzanera, David Filliat
We present CoopNet, an approach that improves the cooperation of co-trained networks by dynamically adapting the apportionment of gradient, to ensure equitable learning progress. I…
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
Adrien Lafage, Mathieu Barbier, Gianni Franchi +1
Accurate trajectory forecasting is crucial for the performance of various systems, such as advanced driver-assistance systems and self-driving vehicles. These forecasts allow us to…
On Double Descent in Reinforcement Learning with LSTD and Random Features
David Brellmann, Eloïse Berthier, David Filliat +1
Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervi…
VIBR: Learning View-Invariant Value Functions for Robust Visual Control
Tom Dupuis, Jaonary Rabarisoa, Quoc-Cuong Pham +1
End-to-end reinforcement learning on images showed significant progress in the recent years. Data-based approach leverage data augmentation and domain randomization while represent…
Latent Discriminant deterministic Uncertainty
Gianni Franchi, Xuanlong Yu, Andrei Bursuc +3
Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensiv…
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
Gianni Franchi, Xuanlong Yu, Andrei Bursuc +5
Predictive uncertainty estimation is essential for safe deployment of Deep Neural Networks in real-world autonomous systems. However, disentangling the different types and sources…
A study of deep perceptual metrics for image quality assessment
Rémi Kazmierczak, Gianni Franchi, Nacim Belkhir +2
Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images. In this work, we propo…
POAR: Efficient Policy Optimization via Online Abstract State Representation Learning
Zhaorun Chen, Siqi Fan, Yuan Tan +6
While the rapid progress of deep learning fuels end-to-end reinforcement learning (RL), direct application, especially in high-dimensional space like robotic scenarios still suffer…
Evaluating Robustness over High Level Driving Instruction for Autonomous Driving
Florence Carton, David Filliat, Jaonary Rabarisoa +1
In recent years, we have witnessed increasingly high performance in the field of autonomous end-to-end driving. In particular, more and more research is being done on driving in ur…
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
Natalia Díaz-Rodríguez, Alberto Lamas, Jules Sanchez +7
The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are…