Invention Grant
- Patent Title: Training and inferencing using a neural network to predict orientations of objects in images
-
Application No.: US16690015Application Date: 2019-11-20
-
Publication No.: US12266144B2Publication Date: 2025-04-01
- Inventor: Siva Karthik Mustikovela , Varun Jampani , Shalini De Mello , Sifei Liu , Umar Iqbal , Jan Kautz
- Applicant: NVIDIA Corporation
- Applicant Address: US CA Santa Clara
- Assignee: NVIDIA Corporation
- Current Assignee: NVIDIA Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Davis Wright Tremaine LLP
- Main IPC: G06V10/24
- IPC: G06V10/24 ; G06F18/21 ; G06F18/214 ; G06N3/045 ; G06N3/08 ; G06T7/73 ; G06V10/44 ; G06V10/764 ; G06V10/778 ; G06V10/82 ; G06V20/56
Abstract:
Apparatuses, systems, and techniques to identify orientations of objects within images. In at least one embodiment, one or more neural networks are trained to identify an orientations of one or more objects based, at least in part, on one or more characteristics of the object other than the object's orientation.
Public/Granted literature
- US20210150757A1 TRAINING AND INFERENCING USING A NEURAL NETWORK TO PREDICT ORIENTATIONS OF OBJECTS IN IMAGES Public/Granted day:2021-05-20
Information query
