Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917644051939328 |
|---|---|
| author | Ji, Ronglei Tekalp, A. Murat |
| author_facet | Ji, Ronglei Tekalp, A. Murat |
| contents | Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing network, which adapts the state-of-the-art superresolution approaches to the deinterlacing task. Our model aligns features from adjacent fields to a reference field (to be deinterlaced) using both deformable convolution residual blocks and self attention. Our extensive experimental results demonstrate that the proposed method provides state-of-the-art deinterlacing results in terms of both numerical and perceptual performance. At the time of writing, our model ranks first in the Full FrameRate LeaderBoard at https://videoprocessing.ai/benchmarks/deinterlacer.html |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_10192 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention Ji, Ronglei Tekalp, A. Murat Image and Video Processing Computer Vision and Pattern Recognition Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing network, which adapts the state-of-the-art superresolution approaches to the deinterlacing task. Our model aligns features from adjacent fields to a reference field (to be deinterlaced) using both deformable convolution residual blocks and self attention. Our extensive experimental results demonstrate that the proposed method provides state-of-the-art deinterlacing results in terms of both numerical and perceptual performance. At the time of writing, our model ranks first in the Full FrameRate LeaderBoard at https://videoprocessing.ai/benchmarks/deinterlacer.html |
| title | Multi-Field De-interlacing using Deformable Convolution Residual Blocks and Self-Attention |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2209.10192 |