AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909540654514176 |
|---|---|
| author | Truong, Quang Trung Kwan, Wong Yuk Nguyen, Duc Thanh Hua, Binh-Son Yeung, Sai-Kit |
| author_facet | Truong, Quang Trung Kwan, Wong Yuk Nguyen, Duc Thanh Hua, Binh-Son Yeung, Sai-Kit |
| contents | Underwater video analysis, hampered by the dynamic marine environment and camera motion, remains a challenging task in computer vision. Existing training-free video generation techniques, learning motion dynamics on the frame-by-frame basis, often produce poor results with noticeable motion interruptions and misaligments. To address these issues, we propose AUTV, a framework for synthesizing marine video data with pixel-wise annotations. We demonstrate the effectiveness of this framework by constructing two video datasets, namely UTV, a real-world dataset comprising 2,000 video-text pairs, and SUTV, a synthetic video dataset including 10,000 videos with segmentation masks for marine objects. UTV provides diverse underwater videos with comprehensive annotations including appearance, texture, camera intrinsics, lighting, and animal behavior. SUTV can be used to improve underwater downstream tasks, which are demonstrated in video inpainting and video object segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations Truong, Quang Trung Kwan, Wong Yuk Nguyen, Duc Thanh Hua, Binh-Son Yeung, Sai-Kit Computational Engineering, Finance, and Science Computer Vision and Pattern Recognition Underwater video analysis, hampered by the dynamic marine environment and camera motion, remains a challenging task in computer vision. Existing training-free video generation techniques, learning motion dynamics on the frame-by-frame basis, often produce poor results with noticeable motion interruptions and misaligments. To address these issues, we propose AUTV, a framework for synthesizing marine video data with pixel-wise annotations. We demonstrate the effectiveness of this framework by constructing two video datasets, namely UTV, a real-world dataset comprising 2,000 video-text pairs, and SUTV, a synthetic video dataset including 10,000 videos with segmentation masks for marine objects. UTV provides diverse underwater videos with comprehensive annotations including appearance, texture, camera intrinsics, lighting, and animal behavior. SUTV can be used to improve underwater downstream tasks, which are demonstrated in video inpainting and video object segmentation. |
| title | AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations |
| topic | Computational Engineering, Finance, and Science Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12828 |