Inventor

KAUTZ JAN

US104 patents

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

KAUTZ JAN

NVIDIA CORP

Three-dimensional (3D) pose estimation from a monocular camera

Transforming convolutional neural networks for visual sequence learning

3D plane detection and reconstruction using a monocular image

Fusing multilayer and multimodal deep neural networks for video classification

Self-supervised single-view 3D reconstruction via semantic consistency

Bilateral convolution layer network for processing point clouds

Systems and methods for pruning neural networks for resource efficient inference

Self-supervised single-view 3D reconstruction via semantic consistency

Domain stylization using a neural network model

Guided hallucination for missing image content using a neural network

Photorealistic image stylization using a neural network model

System and method for optical flow estimation

View synthesis for dynamic scenes

Articulated body mesh estimation using three-dimensional (3D) body keypoints

Iterative spatio-temporal action detection in video

Online detection and classification of dynamic gestures with recurrent convolutional neural networks

Model-based three-dimensional head pose estimation

Gaze tracking system for use in head mounted displays

Training a neural network to predict superpixels using segmentation-aware affinity loss

Equivariant landmark transformation for landmark localization

Learning based camera pose estimation from images of an environment

Machine learning framework applied in a semi-supervised setting to perform instance tracking in a sequence of image frames

Machine-learning-based architecture search method for a neural network

Joint representation learning from images and text

Unconstrained appearance-based gaze estimation

Using residual video data resulting from a compression of original video data to improve a decompression of the original video data

Learning affinity via a spatial propagation neural network

System and method for optical flow estimation

Systems and methods for dynamic facial analysis using a recurrent neural network

Segmentation using an unsupervised neural network training technique

Few-shot viewpoint estimation

Cross-domain image processing for object re-identification

Three-dimensional object reconstruction from a video

Budget-aware method for detecting activity in video

Unsupervised learning approach for video deblurring

Training and inferencing using a neural network to predict orientations of objects in images

Driver gaze tracking system for use in vehicles

Inverse rendering of a scene from a single image

Learning rigidity of dynamic scenes for three-dimensional scene flow estimation

Unified optimization method for end-to-end camera image processing for translating a sensor captured image to a display image

Unified optimization method for end-to-end camera image processing for translating a sensor captured image to a display image

Future object trajectory predictions for autonomous machine applications

Fast multi-scale point cloud registration with a hierarchical gaussian mixture

Semi-supervised learning for landmark localization

Modeling point cloud data using hierarchies of Gaussian mixture models

MICROSOFT CORP

Graphics image rendering with radiance self-transfer for low-frequency lighting environments

Graphics image rendering with radiance self-transfer for low-frequency lighting environments

DISNEY ENTPR INC

3D printing with custom surface reflectance

Content-adaptive lenticular prints

BICKEL BERND

Physical reproduction of reflectance fields