Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914637251870720 |
|---|---|
| author | Álvarez-Tuñón, Olaya Brodskiy, Yury Kayacan, Erdal |
| author_facet | Álvarez-Tuñón, Olaya Brodskiy, Yury Kayacan, Erdal |
| contents | This paper overviews different pose representations and metric functions in visual odometry (VO) networks. The performance of VO networks heavily relies on how their architecture encodes the information. The choice of pose representation and loss function significantly impacts network convergence and generalization. We investigate these factors in the VO network DeepVO by implementing loss functions based on Euler, quaternion, and chordal distance and analyzing their influence on performance. The results of this study provide insights into how loss functions affect the designing of efficient and accurate VO networks for camera motion estimation. The experiments illustrate that a distance that complies with the mathematical requirements of a metric, such as the chordal distance, provides better generalization and faster convergence. The code for the experiments can be found at https://github.com/remaro-network/Loss_VO_right |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05396 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry Álvarez-Tuñón, Olaya Brodskiy, Yury Kayacan, Erdal Computer Vision and Pattern Recognition This paper overviews different pose representations and metric functions in visual odometry (VO) networks. The performance of VO networks heavily relies on how their architecture encodes the information. The choice of pose representation and loss function significantly impacts network convergence and generalization. We investigate these factors in the VO network DeepVO by implementing loss functions based on Euler, quaternion, and chordal distance and analyzing their influence on performance. The results of this study provide insights into how loss functions affect the designing of efficient and accurate VO networks for camera motion estimation. The experiments illustrate that a distance that complies with the mathematical requirements of a metric, such as the chordal distance, provides better generalization and faster convergence. The code for the experiments can be found at https://github.com/remaro-network/Loss_VO_right |
| title | Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.05396 |