Event Collapse in Contrast Maximization Frameworks
Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation. However, it may suffer from a problem called event collapse, which is an undesired solution where events are warped into too...
Main Authors: | Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/14/5190 |
Similar Items
-
A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework
by: Shintaro Shiba, et al.
Published: (2023-03-01) -
Recursive Contrast Maximization for Event-Based High-Frequency Motion Estimation
by: Takehiro Ozawa, et al.
Published: (2022-01-01) -
Optical Flow Estimation by Matching Time Surface with Event-Based Cameras
by: Jun Nagata, et al.
Published: (2021-02-01) -
Event Encryption for Neuromorphic Vision Sensors: Framework, Algorithm, and Evaluation
by: Bowen Du, et al.
Published: (2021-06-01) -
Neuromorphic Eye-in-Hand Visual Servoing
by: Rajkumar Muthusamy, et al.
Published: (2021-01-01)