DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911394374352896 |
|---|---|
| author | Han, Janghyeok Sim, Gyujin Kim, Geonung Lee, Hyun-seung Choi, Kyuha Han, Youngseok Cho, Sunghyun |
| author_facet | Han, Janghyeok Sim, Gyujin Kim, Geonung Lee, Hyun-seung Choi, Kyuha Han, Youngseok Cho, Sunghyun |
| contents | Video super-resolution (VSR) aims to reconstruct a high-resolution (HR) video from a low-resolution (LR) counterpart. Achieving successful VSR requires producing realistic HR details and ensuring both spatial and temporal consistency. To restore realistic details, diffusion-based VSR approaches have recently been proposed. However, the inherent randomness of diffusion, combined with their tile-based approach, often leads to spatio-temporal inconsistencies. In this paper, we propose DC-VSR, a novel VSR approach to produce spatially and temporally consistent VSR results with realistic textures. To achieve spatial and temporal consistency, DC-VSR adopts a novel Spatial Attention Propagation (SAP) scheme and a Temporal Attention Propagation (TAP) scheme that propagate information across spatio-temporal tiles based on the self-attention mechanism. To enhance high-frequency details, we also introduce Detail-Suppression Self-Attention Guidance (DSSAG), a novel diffusion guidance scheme. Comprehensive experiments demonstrate that DC-VSR achieves spatially and temporally consistent, high-quality VSR results, outperforming previous approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03502 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior Han, Janghyeok Sim, Gyujin Kim, Geonung Lee, Hyun-seung Choi, Kyuha Han, Youngseok Cho, Sunghyun Image and Video Processing Artificial Intelligence Graphics Video super-resolution (VSR) aims to reconstruct a high-resolution (HR) video from a low-resolution (LR) counterpart. Achieving successful VSR requires producing realistic HR details and ensuring both spatial and temporal consistency. To restore realistic details, diffusion-based VSR approaches have recently been proposed. However, the inherent randomness of diffusion, combined with their tile-based approach, often leads to spatio-temporal inconsistencies. In this paper, we propose DC-VSR, a novel VSR approach to produce spatially and temporally consistent VSR results with realistic textures. To achieve spatial and temporal consistency, DC-VSR adopts a novel Spatial Attention Propagation (SAP) scheme and a Temporal Attention Propagation (TAP) scheme that propagate information across spatio-temporal tiles based on the self-attention mechanism. To enhance high-frequency details, we also introduce Detail-Suppression Self-Attention Guidance (DSSAG), a novel diffusion guidance scheme. Comprehensive experiments demonstrate that DC-VSR achieves spatially and temporally consistent, high-quality VSR results, outperforming previous approaches. |
| title | DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior |
| topic | Image and Video Processing Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2502.03502 |