Motion-Adaptive Inference for Flexible Learned B-Frame Compression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929242342686720 |
|---|---|
| author | Yilmaz, M. Akin Ulas, O. Ugur Bilican, Ahmet Tekalp, A. Murat |
| author_facet | Yilmaz, M. Akin Ulas, O. Ugur Bilican, Ahmet Tekalp, A. Murat |
| contents | While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The performance gap is bigger for complex scenes with large motions. This is related to the fact that the distance between the past and future references vary in hierarchical B-frame compression depending on the level of hierarchy, which causes motion range to vary. The inability of a single B-frame compression model to adapt to various motion ranges causes loss of performance. As a remedy, we propose controlling the motion range for flow prediction during inference (to approximately match the range of motions in the training data) by downsampling video frames adaptively according to amount of motion and level of hierarchy in order to compress all B-frames using a single flexible-rate model. We present state-of-the-art BD rate results to demonstrate the superiority of our proposed single-model motion-adaptive inference approach to all existing learned B-frame compression models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08550 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Motion-Adaptive Inference for Flexible Learned B-Frame Compression Yilmaz, M. Akin Ulas, O. Ugur Bilican, Ahmet Tekalp, A. Murat Image and Video Processing While the performance of recent learned intra and sequential video compression models exceed that of respective traditional codecs, the performance of learned B-frame compression models generally lag behind traditional B-frame coding. The performance gap is bigger for complex scenes with large motions. This is related to the fact that the distance between the past and future references vary in hierarchical B-frame compression depending on the level of hierarchy, which causes motion range to vary. The inability of a single B-frame compression model to adapt to various motion ranges causes loss of performance. As a remedy, we propose controlling the motion range for flow prediction during inference (to approximately match the range of motions in the training data) by downsampling video frames adaptively according to amount of motion and level of hierarchy in order to compress all B-frames using a single flexible-rate model. We present state-of-the-art BD rate results to demonstrate the superiority of our proposed single-model motion-adaptive inference approach to all existing learned B-frame compression models. |
| title | Motion-Adaptive Inference for Flexible Learned B-Frame Compression |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2402.08550 |