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: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5190 |
| _version_ | 1797415995000750080 |
|---|---|
| author | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego |
| author_facet | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego |
| author_sort | Shintaro Shiba |
| collection | DOAJ |
| description | 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 few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space–time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models. |
| first_indexed | 2024-03-09T05:57:30Z |
| format | Article |
| id | doaj.art-acf37871f9234a919958029c4bc351bb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:57:30Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-acf37871f9234a919958029c4bc351bb2023-12-03T12:12:27ZengMDPI AGSensors1424-82202022-07-012214519010.3390/s22145190Event Collapse in Contrast Maximization FrameworksShintaro Shiba0Yoshimitsu Aoki1Guillermo Gallego2Department of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Kohoku-ku, Yokohama 223-8522, Kanagawa, JapanDepartment of Electronics and Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1, Kohoku-ku, Yokohama 223-8522, Kanagawa, JapanDepartment of Electrical Engineering and Computer Science, Technische Universität Berlin, 10587 Berlin, GermanyContrast 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 few pixels. As prior works have largely ignored the issue or proposed workarounds, it is imperative to analyze this phenomenon in detail. Our work demonstrates event collapse in its simplest form and proposes collapse metrics by using first principles of space–time deformation based on differential geometry and physics. We experimentally show on publicly available datasets that the proposed metrics mitigate event collapse and do not harm well-posed warps. To the best of our knowledge, regularizers based on the proposed metrics are the only effective solution against event collapse in the experimental settings considered, compared with other methods. We hope that this work inspires further research to tackle more complex warp models.https://www.mdpi.com/1424-8220/22/14/5190computer visionintelligent sensorsroboticsevent-based cameracontrast maximizationoptical flow |
| spellingShingle | Shintaro Shiba Yoshimitsu Aoki Guillermo Gallego Event Collapse in Contrast Maximization Frameworks Sensors computer vision intelligent sensors robotics event-based camera contrast maximization optical flow |
| title | Event Collapse in Contrast Maximization Frameworks |
| title_full | Event Collapse in Contrast Maximization Frameworks |
| title_fullStr | Event Collapse in Contrast Maximization Frameworks |
| title_full_unstemmed | Event Collapse in Contrast Maximization Frameworks |
| title_short | Event Collapse in Contrast Maximization Frameworks |
| title_sort | event collapse in contrast maximization frameworks |
| topic | computer vision intelligent sensors robotics event-based camera contrast maximization optical flow |
| url | https://www.mdpi.com/1424-8220/22/14/5190 |
| work_keys_str_mv | AT shintaroshiba eventcollapseincontrastmaximizationframeworks AT yoshimitsuaoki eventcollapseincontrastmaximizationframeworks AT guillermogallego eventcollapseincontrastmaximizationframeworks |