Skip to main content

Raquel Urtasun

Recent publications

Efficient Graph Generation with Graph Recurrent Attention Networks

Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehicles

Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization

Identifying Unknown Instances for Autonomous Driving

Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction

DSIC: Deep Stereo Image Compression

Learning Joint 2D-3D Representations for Depth Completion

DAGMapper: Learning to Map by Discovering Lane Topology

DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

End-to-End Interpretable Neural Motion Planner

UPSNet: A Unified Panoptic Segmentation Network

Convolutional Recurrent Network for Road Boundary Extraction

Learning to Localize Through Compressed Binary Maps

Multi-Task Multi-Sensor Fusion for 3D Object Detection

DARNet: Deep Active Ray Network for Building Segmentation

Deep Rigid Instance Scene Flow

DeepSignals: Predicting Intent of Drivers Through Visual Signals

LanczosNet: Multi-Scale Deep Graph Convolutional Networks

Graph HyperNetworks for Neural Architecture Search

Dimensionality Reduction for Representing the Knowledge of Probabilistic Models

Neural Guided Constraint Logic Programming for Program Synthesis

Deep Multi-Sensor Lane Detection

IntentNet: Learning to Predict Intention from Raw Sensor Data

HDNET: Exploiting HD Maps for 3D Object Detection

Learning to Localize Using a LiDAR Intensity Map

Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds

Single Image Intrinsic Decomposition Without a Single Intrinsic Image

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

End-to-End Deep Structured Models for Drawing Crosswalks

PIXOR: Real-Time 3D Object Detection from Point Clouds

Learning Deep Structured Active Contours End-to-End

Matching Adversarial Networks

SurfConv: Bridging 3D and 2D Convolution for RGBD Images

SBNet: Sparse Blocks Network for Fast Inference

Hierarchical Recurrent Attention Networks for Structured Online Maps

Deep Parametric Continuous Convolutional Neural Networks

Fast and Furious: Real-Time End-to-End 3D Detection, Tracking, and Motion Forecasting with a Single Convolutional Net

GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

MultiNet: Real-Time Joint Semantic Reasoning for Autonomous Driving

End-to-End Learning of Multi-Sensor 3D Tracking by Detection

Learning to Reweight Examples for Robust Deep Learning

Reviving and Improving Recurrent Back-Propagation

Inference in Probabilistic Graphical Models by Graph Neural Networks

Leveraging Constraint Logic Programming for Neural Guided Program Synthesis

Graph Partition Neural Networks for Semi-Supervised Classification

The Reversible Residual Network: Backpropagation Without Storing Activations

Few-Shot Learning Through an Information Retrieval Lens

Situation Recognition with Graph Neural Networks

TorontoCity: Seeing the World with a Million Eyes

Be Your Own Prada: Fashion Synthesis with Structural Coherence

SGN: Sequential Grouping Networks for Instance Segmentation

3D Graph Neural Networks for RGBD Semantic Segmentation

Towards Diverse and Natural Image Descriptions via a Conditional GAN

DeepRoadMapper: Extracting Road Topology from Aerial Images

Efficient Multiple Instance Metric Learning Using Weakly Supervised Data

Annotating Object Instances with a Polygon-RNN

Deep Watershed Transform for Instance Segmentation

Sports Field Localization via Deep Structured Models

Deep Spectral Clustering Learning

Find Your Way by Observing the Sun and Other Semantic Cues

Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes