Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2503.04665 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915184418750464 |
|---|---|
| author | Aiyetigbo, Mary Yuan, Wanqi Luo, Feng Li, Nianyi |
| author_facet | Aiyetigbo, Mary Yuan, Wanqi Luo, Feng Li, Nianyi |
| contents | We present a novel approach for super-resolution that utilizes implicit neural representation (INR) to effectively reconstruct and enhance low-resolution videos and images. By leveraging the capacity of neural networks to implicitly encode spatial and temporal features, our method facilitates high-resolution reconstruction using only low-resolution inputs and a 3D high-resolution grid. This results in an efficient solution for both image and video super-resolution. Our proposed method, SR-INR, maintains consistent details across frames and images, achieving impressive temporal stability without relying on the computationally intensive optical flow or motion estimation typically used in other video super-resolution techniques. The simplicity of our approach contrasts with the complexity of many existing methods, making it both effective and efficient. Experimental evaluations show that SR-INR delivers results on par with or superior to state-of-the-art super-resolution methods, while maintaining a more straightforward structure and reduced computational demands. These findings highlight the potential of implicit neural representations as a powerful tool for reconstructing high-quality, temporally consistent video and image signals from low-resolution data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04665 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Implicit Neural Representation for Video and Image Super-Resolution Aiyetigbo, Mary Yuan, Wanqi Luo, Feng Li, Nianyi Computer Vision and Pattern Recognition We present a novel approach for super-resolution that utilizes implicit neural representation (INR) to effectively reconstruct and enhance low-resolution videos and images. By leveraging the capacity of neural networks to implicitly encode spatial and temporal features, our method facilitates high-resolution reconstruction using only low-resolution inputs and a 3D high-resolution grid. This results in an efficient solution for both image and video super-resolution. Our proposed method, SR-INR, maintains consistent details across frames and images, achieving impressive temporal stability without relying on the computationally intensive optical flow or motion estimation typically used in other video super-resolution techniques. The simplicity of our approach contrasts with the complexity of many existing methods, making it both effective and efficient. Experimental evaluations show that SR-INR delivers results on par with or superior to state-of-the-art super-resolution methods, while maintaining a more straightforward structure and reduced computational demands. These findings highlight the potential of implicit neural representations as a powerful tool for reconstructing high-quality, temporally consistent video and image signals from low-resolution data. |
| title | Implicit Neural Representation for Video and Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04665 |