Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels
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_ | 1866909374190977024 |
|---|---|
| author | Pogorelyuk, Leonid Radev, Stefan T. |
| author_facet | Pogorelyuk, Leonid Radev, Stefan T. |
| contents | We propose a new contrastive objective for learning overcomplete pixel-level features that are invariant to motion blur. Other invariances (e.g., pose, illumination, or weather) can be learned by applying the corresponding transformations on unlabeled images during self-supervised training. We showcase that a simple U-Net trained with our objective can produce local features useful for aligning the frames of an unseen video captured with a moving camera under realistic and challenging conditions. Using a carefully designed toy example, we also show that the overcomplete pixels can encode the identity of objects in an image and the pixel coordinates relative to these objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07410 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels Pogorelyuk, Leonid Radev, Stefan T. Computer Vision and Pattern Recognition We propose a new contrastive objective for learning overcomplete pixel-level features that are invariant to motion blur. Other invariances (e.g., pose, illumination, or weather) can be learned by applying the corresponding transformations on unlabeled images during self-supervised training. We showcase that a simple U-Net trained with our objective can produce local features useful for aligning the frames of an unseen video captured with a moving camera under realistic and challenging conditions. Using a carefully designed toy example, we also show that the overcomplete pixels can encode the identity of objects in an image and the pixel coordinates relative to these objects. |
| title | Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.07410 |