Adrien David GAIDON

METHOD FOR DIVERSE SEQUENTIAL POINT CLOUD FORECASTING

MULTI-OBJECT 3D SHAPE COMPLETION IN THE WILD FROM A SINGLE RGB-D IMAGE VIA LATENT 3D OCTMAE

SYSTEMS AND METHODS FOR UNCERTAINTY AWARE MONOCULAR 3D OBJECT DETECTION

MULTI-VIEW DEPTH ESTIMATION LEVERAGING OFFLINE STRUCTURE-FROM-MOTION

FUSING NEURAL RADIANCE FIELDS BY REGISTRATION AND BLENDING

SYSTEMS AND METHODS FOR GENERATING AN IMAGE USING INTERPOLATION OF FEATURES

SCALE-AWARE DEPTH ESTIMATION USING MULTI-CAMERA PROJECTION LOSS

METHOD FOR DIVERSE SEQUENTIAL POINT CLOUD FORECASTING

INCREMENTAL MAP BUILDING USING LEARNABLE FEATURES AND DESCRIPTORS

NEURAL IMPLICIT SCATTERING FUNCTIONS FOR INVERSE PARAMETER ESTIMATION AND DYNAMICS MODELING OF MULTI-OBJECT INTERACTIONS

LEARNING LATENT-SPACE BARRIER FUNCTIONS FROM SAFE DEMONSTRATIONS

SYSTEM AND METHOD FOR TRAINING A MULTI-VIEW 3D OBJECT DETECTION FRAMEWORK

SYSTEM AND METHOD FOR RISK-BIASED TRAJECTORY FORECASTING

ADVERSARIAL OBJECT-AWARE NEURAL SCENE RENDERING FOR 3D OBJECT DETECTION

Semantically aware keypoint matching

SYSTEM AND METHOD OF CONDITIONAL NEURAL FLOORPLANS FOR STATIC-DYNAMIC DISENTANGLEMENT

Depth estimation based on ego-motion estimation and residual flow estimation

Self-supervised monocular depth estimation via rigid-motion embeddings

Systems and methods for uncertainty aware monocular 3D object detection

Monocular object detection via end-to-end differentiable pipeline

Neural architecture search for fusing multiple networks into one

PRODUCING A DEPTH MAP FROM TWO-DIMENSIONAL IMAGES

Producing a depth map from a monocular two-dimensional image

SYSTEMS AND METHODS FOR DYNAMICS-AWARE COMPARISON OF REWARD FUNCTIONS

Systems and methods for self-supervised learning of camera intrinsic parameters from a sequence of images

Systems and methods for reconstructing a scene in three dimensions from a two-dimensional image

Systems and methods for jointly training a machine-learning-based monocular optical flow, depth, and scene flow estimator

Systems and methods for jointly training a machine-learning-based monocular optical flow, depth, and scene flow estimator

Learning monocular 3D object detection from 2D semantic keypoint detection

Systems and methods for dataset and model management for multi-modal auto-labeling and active learning

Systems and methods for training a machine-learning-based monocular depth estimator

Systems and methods to train a prediction system for depth perception

Network architecture for monocular depth estimation and object detection

System and method for training a multi-task model

System and method for training an adapter network to improve transferability to real-world datasets

Evaluation process for a multi-task network

System and method for tracking occluded objects

System and method for generating a training set for improving monocular object detection

Monocular depth supervision from 3D bounding boxes

System and method for estimating depth uncertainty for self-supervised 3D reconstruction

Using a bird's eye view feature map, augmented with semantic information, to detect an object in an environment

Systems and methods for risk-sensitive sequential action control for robotic devices

Systems and methods for trajectory forecasting according to semantic category uncertainty

Systems and methods for training a machine-learning-based monocular depth estimator

Mixed-batch training of a multi-task network

Camera agnostic depth network

Network architecture for the joint learning of monocular depth prediction and completion

Training of joint depth prediction and completion

Sparse auxiliary network for depth completion

Multi-scale recurrent decoder for monocular depth estimation

Systems and methods for controlling a robot

Causing a mobile robot to move according to a planned trajectory determined from a prediction of agent states of agents in an environment of the mobile robot

System and method for generating a point cloud that includes surface normal information

Method and system for behavioral cloning of autonomous driving policies for safe autonomous agents

SYSTEM AND METHOD FOR TRAINING OF A DETECTOR MODEL TO OUTPUT AN INSTANCE IDENTIFIER INDICATING OBJECT CONSISTENCY ALONG THE TEMPORAL AXIS

Game-theoretic planning for risk-aware interactive agents

Multi-view depth estimation leveraging offline structure-from-motion

System and method for self-supervised monocular depth regularization from surface normals

Pixel-wise residual pose estimation for monocular depth estimation

Camera agnostic depth network

Monocular depth supervision from 3D bounding boxes

Multi-scale recurrent decoder for monocular depth estimation

Producing a bird's eye view image from a two dimensional image

Systems and methods for using a joint feature space to identify driving behaviors

Using a multimode neural network to determine a representation of a spatial structure objects in an image

Using a neural network to produce a digital map for a location

Systems and methods for self-supervised residual flow estimation

Neural architecture search system for generating a neural network architecture

Invertible depth network for image reconstruction and domain transfers

System and method for generating feature space data

Bird's eye view based velocity estimation

Bird's eye view based velocity estimation via self-supervised learning

System and method for estimating depth uncertainty for self-supervised 3D reconstruction

Panoptic generative adversarial network with explicit modeling of category and instance information

Neural architecture search for fusing multiple networks into one

Keypoint matching using graph convolutions

Depth estimation based on ego-motion estimation and residual flow estimation

Meta-learning neural architecture search via graph networks on search space lattices

Semantically aware keypoint matching

Incremental map building using learnable features and descriptors

Simulation-based learning of driver interactions through a vehicle window

System and method for trajectory prediction using a predicted endpoint conditioned network

Systems and methods for self-supervised depth estimation according to an arbitrary camera

System and method for predicting the movement of pedestrians

Self-supervised 3D keypoint learning for monocular visual odometry

Self-supervised 3D keypoint learning for ego-motion estimation

Systems and methods for panoptic image segmentation

3D auto-labeling with structural and physical constraints

Systems and methods for self-supervised scale-aware training of a model for monocular depth estimation

Systems and methods for depth estimation using monocular images

Systems and methods for depth estimation using semantic features

Systems and methods for conditioning training data to avoid learned aberrations

Systems and methods for semi-supervised training using reprojected distance loss

Systems and methods for semi-supervised depth estimation according to an arbitrary camera

Network architecture for ego-motion estimation

Systems and methods for weakly supervised training of a model for monocular depth estimation

Auto-labeling of driving logs using analysis-by-synthesis and unsupervised domain adaptation

Systems and methods for depth estimation using monocular images

Fusing predictions for end-to-end panoptic segmentation