RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915253286076416 |
|---|---|
| author | Wu, Biao Zhang, Diankai Liu, Shaoli Gao, Si Zheng, Chengjian Wang, Ning |
| author_facet | Wu, Biao Zhang, Diankai Liu, Shaoli Gao, Si Zheng, Chengjian Wang, Ning |
| contents | As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated state-of-the-art performance in spatial-temporal super-resolution tasks, their computationally intensive nature poses significant deployment challenges for resource-constrained edge devices, particularly in real-time mobile video processing scenarios where power efficiency and latency constraints coexist. In this work, we propose a Reparameterizable Architecture for High Fidelity Video Super Resolution method, named RepNet-VSR, for real-time 4x video super-resolution. On the REDS validation set, the proposed model achieves 27.79 dB PSNR when processing 180p to 720p frames in 103 ms per 10 frames on a MediaTek Dimensity NPU. The competition results demonstrate an excellent balance between restoration quality and deployment efficiency. The proposed method scores higher than the previous champion algorithm of MAI video super-resolution challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15649 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution Wu, Biao Zhang, Diankai Liu, Shaoli Gao, Si Zheng, Chengjian Wang, Ning Image and Video Processing Computer Vision and Pattern Recognition As a fundamental challenge in visual computing, video super-resolution (VSR) focuses on reconstructing highdefinition video sequences from their degraded lowresolution counterparts. While deep convolutional neural networks have demonstrated state-of-the-art performance in spatial-temporal super-resolution tasks, their computationally intensive nature poses significant deployment challenges for resource-constrained edge devices, particularly in real-time mobile video processing scenarios where power efficiency and latency constraints coexist. In this work, we propose a Reparameterizable Architecture for High Fidelity Video Super Resolution method, named RepNet-VSR, for real-time 4x video super-resolution. On the REDS validation set, the proposed model achieves 27.79 dB PSNR when processing 180p to 720p frames in 103 ms per 10 frames on a MediaTek Dimensity NPU. The competition results demonstrate an excellent balance between restoration quality and deployment efficiency. The proposed method scores higher than the previous champion algorithm of MAI video super-resolution challenge. |
| title | RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15649 |