Invention Application
- Patent Title: SELF-SUPERVISED SINGLE-VIEW 3D RECONSTRUCTION VIA SEMANTIC CONSISTENCY
-
Application No.: US16849962Application Date: 2020-04-15
-
Publication No.: US20210287430A1Publication Date: 2021-09-16
- Inventor: Xueting Li , Sifei Liu , Kihwan Kim , Shalini De Mello , Varun Jampani , 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
- Main IPC: G06T17/20
- IPC: G06T17/20 ; G06T7/73 ; G06T7/40 ; G06K9/62
Abstract:
Apparatuses, systems, and techniques to identify a shape or camera pose of a three-dimensional object from a two-dimensional image of the object. In at least one embodiment, objects are identified in an image using one or more neural networks that have been trained on objects of a similar category and a three-dimensional mesh template.
Public/Granted literature
- US11238650B2 Self-supervised single-view 3D reconstruction via semantic consistency Public/Granted day:2022-02-01
Information query
