A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914700288065536 |
|---|---|
| author | Shiba, Shintaro Aoki, Yoshimitsu Gallego, Guillermo |
| author_facet | Shiba, Shintaro Aoki, Yoshimitsu Gallego, Guillermo |
| contents | Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_07350 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework Shiba, Shintaro Aoki, Yoshimitsu Gallego, Guillermo Computer Vision and Pattern Recognition Robotics Differential Geometry Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras. |
| title | A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework |
| topic | Computer Vision and Pattern Recognition Robotics Differential Geometry |
| url | https://arxiv.org/abs/2212.07350 |