Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.06172 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911255756800000 |
|---|---|
| author | Chang, Hua Xu, Xin Liu, Wei Wang, Wei Yuan, Xin Jiang, Kui |
| author_facet | Chang, Hua Xu, Xin Liu, Wei Wang, Wei Yuan, Xin Jiang, Kui |
| contents | Chinese opera is celebrated for preserving classical art. However, early filming equipment limitations have degraded videos of last-century performances by renowned artists (e.g., low frame rates and resolution), hindering archival efforts. Although space-time video super-resolution (STVSR) has advanced significantly, applying it directly to opera videos remains challenging. The scarcity of datasets impedes the recovery of high frequency details, and existing STVSR methods lack global modeling capabilities, compromising visual quality when handling opera's characteristic large motions. To address these challenges, we pioneer a large scale Chinese Opera Video Clip (COVC) dataset and propose the Mamba-based multiscale fusion network for space-time Opera Video Super-Resolution (MambaOVSR). Specifically, MambaOVSR involves three novel components: the Global Fusion Module (GFM) for motion modeling through a multiscale alternating scanning mechanism, and the Multiscale Synergistic Mamba Module (MSMM) for alignment across different sequence lengths. Additionally, our MambaVR block resolves feature artifacts and positional information loss during alignment. Experimental results on the COVC dataset show that MambaOVSR significantly outperforms the SOTA STVSR method by an average of 1.86 dB in terms of PSNR. Dataset and Code will be publicly released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-Resolution Chang, Hua Xu, Xin Liu, Wei Wang, Wei Yuan, Xin Jiang, Kui Computer Vision and Pattern Recognition Artificial Intelligence Chinese opera is celebrated for preserving classical art. However, early filming equipment limitations have degraded videos of last-century performances by renowned artists (e.g., low frame rates and resolution), hindering archival efforts. Although space-time video super-resolution (STVSR) has advanced significantly, applying it directly to opera videos remains challenging. The scarcity of datasets impedes the recovery of high frequency details, and existing STVSR methods lack global modeling capabilities, compromising visual quality when handling opera's characteristic large motions. To address these challenges, we pioneer a large scale Chinese Opera Video Clip (COVC) dataset and propose the Mamba-based multiscale fusion network for space-time Opera Video Super-Resolution (MambaOVSR). Specifically, MambaOVSR involves three novel components: the Global Fusion Module (GFM) for motion modeling through a multiscale alternating scanning mechanism, and the Multiscale Synergistic Mamba Module (MSMM) for alignment across different sequence lengths. Additionally, our MambaVR block resolves feature artifacts and positional information loss during alignment. Experimental results on the COVC dataset show that MambaOVSR significantly outperforms the SOTA STVSR method by an average of 1.86 dB in terms of PSNR. Dataset and Code will be publicly released. |
| title | MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-Resolution |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.06172 |