Dense Matchers for Dense Tracking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914687535284224 |
|---|---|
| author | Jelínek, Tomáš Šerých, Jonáš Matas, Jiří |
| author_facet | Jelínek, Tomáš Šerých, Jonáš Matas, Jiří |
| contents | Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not been extensively explored. This paper extends the concept of combining multiple optical flows over logarithmically spaced intervals as proposed by MFT. We demonstrate the compatibility of MFT with different optical flow networks, yielding results that surpass their individual performance. Moreover, we present a simple yet effective combination of these networks within the MFT framework. This approach proves to be competitive with more sophisticated, non-causal methods in terms of position prediction accuracy, highlighting the potential of MFT in enhancing long-term tracking applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11287 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dense Matchers for Dense Tracking Jelínek, Tomáš Šerých, Jonáš Matas, Jiří Computer Vision and Pattern Recognition Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not been extensively explored. This paper extends the concept of combining multiple optical flows over logarithmically spaced intervals as proposed by MFT. We demonstrate the compatibility of MFT with different optical flow networks, yielding results that surpass their individual performance. Moreover, we present a simple yet effective combination of these networks within the MFT framework. This approach proves to be competitive with more sophisticated, non-causal methods in terms of position prediction accuracy, highlighting the potential of MFT in enhancing long-term tracking applications. |
| title | Dense Matchers for Dense Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.11287 |