Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914830160494592 |
|---|---|
| author | Danier, Duolikun Zhang, Fan Bull, David |
| author_facet | Danier, Duolikun Zhang, Fan Bull, David |
| contents | This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction. This model first extracts spatio-temporal features at multiple scales using a 3D CNN, and estimates multi-flows using these features in a coarse-to-fine manner. The estimated multi-flows are then used to warp the original input frames as well as context maps, and the warped results are fused by a synthesis network to produce the final output. This VFI approach has been fully evaluated against 12 state-of-the-art VFI methods on three commonly used test databases. The results evidently show the effectiveness of the proposed method, which offers superior interpolation performance over other state of the art algorithms, with PSNR gains up to 0.19dB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_07731 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN Danier, Duolikun Zhang, Fan Bull, David Computer Vision and Pattern Recognition Image and Video Processing This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction. This model first extracts spatio-temporal features at multiple scales using a 3D CNN, and estimates multi-flows using these features in a coarse-to-fine manner. The estimated multi-flows are then used to warp the original input frames as well as context maps, and the warped results are fused by a synthesis network to produce the final output. This VFI approach has been fully evaluated against 12 state-of-the-art VFI methods on three commonly used test databases. The results evidently show the effectiveness of the proposed method, which offers superior interpolation performance over other state of the art algorithms, with PSNR gains up to 0.19dB. |
| title | Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2202.07731 |