Automatic Dense Annotation for Monocular 3D Scene Understanding

Automatic Dense Annotation for Monocular 3D Scene Understanding

Deep neural networks have revolutionized many areas of computer vision, but they require notoriously large amounts of labeled training data. For tasks such as semantic segmentation and monocular 3d scene layout estimation, collecting high-quality training data is extremely laborious because dense, p...

Full description

Bibliographic Details
Main Authors: Md Alimoor Reza, Kai Chen, Akshay Naik, David J. Crandall, Soon-Heung Jung
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Scene understanding
3D reconstruction
semi-supervised learning
computer vision
Online Access:https://ieeexplore.ieee.org/document/9052727/

Internet

https://ieeexplore.ieee.org/document/9052727/

Similar Items