Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Adrien Gaidon, PhD
About me
Selected Talks
Published:
Posts
My first (placeholder) blog
Published:
Welcome to my blog! Nothing interesting for now, but will try to post some things from time to time!
publications
Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
Published:
A new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions.
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
Published:
A new dataset (STIP) and graph neural network operating on scene graphs to predict pedestrian crossing intent.
3D Packing for Self-Supervised Monocular Depth Estimation
Published:
A new state of the art in self-supervised monocular depth estimation (PackNet), a new benchmark (DDAD), and weak velocity supervision.
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors”
Published:
An automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data.
Real-Time Panoptic Segmentation from Dense Detections
Published:
A novel panoptic segmentation method featuring parameter-free instance mask reconstruction, state-of-the-art accuracy, and real-time inference.
Spatio-Temporal Graph for Video Captioning with Knowledge Distillation
Published:
A model that learns to distill spatio-temporal object interactions for video captioning.
Differentiable Rendering: A Survey
Published:
A review of the literature and current state of differentiable rendering, its applications, and open research problems.
Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
Published:
A hierarchical reinforcement and imitation learning (H-ReIL) approach for learning to drive in near-accident scenarios.
Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion
Published:
Neural Ray Surfaces (NRS) are convolutional networks that represent pixel-wise projection rays, approximating a wide range of cameras. NRS are fully differentiable and can be learned end-to-end from unlabeled raw videos.
Monocular Differentiable Rendering for Self-Supervised 3D Object Detection
Published:
Novel self-supervised method for textured 3D shape reconstruction and pose estimation of rigid objects with the help of strong shape priors and 2D instance masks.
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
Published:
Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction via endpoint inference.
Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Published:
A method to automatically find planner-specific defects of autonomous vehicles in simulation.
Behaviorally Diverse Traffic Simulation via Reinforcement Learning
Published:
Reinforcement Learning of autonomous driving agent policies to balance driving skills and behavioral diversity.
Driving Through Ghosts: Behavioral Cloning with False Positives
Published:
A novel representation of perceptual uncertainty for learning to plan via behaviorial cloning.
End-to-end Birds-eye-view Flow Estimation for Autonomous Driving
Published:
An end-to-end deep learning framework for LIDAR-based flow estimation in 2.5D bird’s eye view (BeV). We show it boosts tracking performance on a real-world autonomous car.
Game-Theoretic Planning for Risk-Aware Interactive Agents
Published:
A risk-sensitive game-theoretic planning algorithm to model complex multi-agent interactions yielding more time-efficient, intuitive, and safe behaviors when facing underlying risks and uncertainty.
Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction
Published:
An online framework for safe and efficient crowd-robot interaction using sampling based trajectory forecasting with risk-sensitive optimal control.
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Published:
We propose a data-dependent regularization technique for heteroskedastic and imbalanced datasets.
Monocular Depth Estimation for Soft Visuotactile Sensors
Published:
We show monocular depth estimation methods can work inside small fluid-filled visuotactile sensors like Soft-Bubbles.
RAT iLQR: A Risk Auto-Tuning Controller to Optimally Account for Stochastic Model Mismatch
Published:
Hierarchical Lovasz Embeddings for Proposal-free Panoptic Segmentation
Published:
We learn per pixel feature vectors that simultaneously encode instance- and category-level discriminative information.
Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion
Published:
Learning a single network for dialable depth perception, with or without sparse LiDAR input.