Inventor

PILLAI SUDEEP

US45 patents

⚠️ This page may combine multiple inventors who share the name “PILLAI SUDEEP”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

PILLAI SUDEEP

TOYOTA RES INST INC

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

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

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

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

Camera agnostic depth network

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

Network architecture for ego-motion estimation

Systems and methods for depth estimation using monocular images

Keypoint matching using graph convolutions

Systems and methods for vehicle light signal classification

Systems and methods for training a neural keypoint detection network

System and method for determining if a vehicle is parked

Systems and methods for generic visual odometry using learned features via neural camera models

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

Monocular 3D vehicle modeling and auto-labeling using semantic keypoints

Camera agnostic depth network

Systems and methods for end-to-end map building from a video sequence using neural camera models

Systems and methods for generic visual odometry using learned features via neural camera models

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

Monocular 3D vehicle modeling and auto-labeling using semantic keypoints

End-to-end signalized intersection transition state estimator with scene graphs over semantic keypoints

Self-supervised 3D keypoint learning for monocular visual odometry

Systems and methods for detecting and matching keypoints between different views of a scene

End-to-end signalized intersection transition state estimator with scene graphs over semantic keypoints

Systems and methods for traffic light detection and classification

Traffic light active learning pipeline

Traffic light active learning pipeline

Incremental map building using learnable features and descriptors

Systems and methods for soft model assertions

Producing a bird&#39;s eye view image from a two dimensional image

System and method for monocular depth estimation from semantic information

System and method for self-supervised depth and ego-motion overfitting

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

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

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

Bird&#39;s eye view based velocity estimation via self-supervised learning

Semi-supervised 3D object tracking in videos via 2D semantic keypoints

End-to-end monocular 2D semantic keypoint detector and tracker learning

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

Traffic light detection auto-labeling and federated learning based on vehicle-to-infrastructure communications

Monocular 2D semantic keypoint detection and tracking

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

MASSACHUSETTS INST TECHNOLOGY

High-speed and tunable scene reconstruction systems and methods using stereo imagery

CAPITAL ONE SERVICES LLC

Systems and methods for dynamically scaling remote resources

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

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