Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.18745 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910719660785664 |
|---|---|
| author | Zhang, Zheyan Klabjan, Diego Manworren, Renee CB |
| author_facet | Zhang, Zheyan Klabjan, Diego Manworren, Renee CB |
| contents | In this work, we address a challenge in video inpainting: reconstructing occluded regions in dynamic, real-world scenarios. Motivated by the need for continuous human motion monitoring in healthcare settings, where facial features are frequently obscured, we propose a diffusion-based video-level inpainting model, DiffMVR. Our approach introduces a dynamic dual-guided image prompting system, leveraging adaptive reference frames to guide the inpainting process. This enables the model to capture both fine-grained details and smooth transitions between video frames, offering precise control over inpainting direction and significantly improving restoration accuracy in challenging, dynamic environments. DiffMVR represents a significant advancement in the field of diffusion-based inpainting, with practical implications for real-time applications in various dynamic settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18745 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DiffMVR: Diffusion-based Automated Multi-Guidance Video Restoration Zhang, Zheyan Klabjan, Diego Manworren, Renee CB Computer Vision and Pattern Recognition In this work, we address a challenge in video inpainting: reconstructing occluded regions in dynamic, real-world scenarios. Motivated by the need for continuous human motion monitoring in healthcare settings, where facial features are frequently obscured, we propose a diffusion-based video-level inpainting model, DiffMVR. Our approach introduces a dynamic dual-guided image prompting system, leveraging adaptive reference frames to guide the inpainting process. This enables the model to capture both fine-grained details and smooth transitions between video frames, offering precise control over inpainting direction and significantly improving restoration accuracy in challenging, dynamic environments. DiffMVR represents a significant advancement in the field of diffusion-based inpainting, with practical implications for real-time applications in various dynamic settings. |
| title | DiffMVR: Diffusion-based Automated Multi-Guidance Video Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.18745 |