Super Efficient Neural Network for Compression Artifacts Reduction and Super Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929225003433984 |
|---|---|
| author | Ma, Wen Lou, Qiuwen Kazemi, Arman Faraone, Julian Afzal, Tariq |
| author_facet | Ma, Wen Lou, Qiuwen Kazemi, Arman Faraone, Julian Afzal, Tariq |
| contents | Video quality can suffer from limited internet speed while being streamed by users. Compression artifacts start to appear when the bitrate decreases to match the available bandwidth. Existing algorithms either focus on removing the compression artifacts at the same video resolution, or on upscaling the video resolution but not removing the artifacts. Super resolution-only approaches will amplify the artifacts along with the details by default. We propose a lightweight convolutional neural network (CNN)-based algorithm which simultaneously performs artifacts reduction and super resolution (ARSR) by enhancing the feature extraction layers and designing a custom training dataset. The output of this neural network is evaluated for test streams compressed at low bitrates using variable bitrate (VBR) encoding. The output video quality shows a 4-6 increase in video multi-method assessment fusion (VMAF) score compared to traditional interpolation upscaling approaches such as Lanczos or Bicubic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14641 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Super Efficient Neural Network for Compression Artifacts Reduction and Super Resolution Ma, Wen Lou, Qiuwen Kazemi, Arman Faraone, Julian Afzal, Tariq Computer Vision and Pattern Recognition Image and Video Processing Video quality can suffer from limited internet speed while being streamed by users. Compression artifacts start to appear when the bitrate decreases to match the available bandwidth. Existing algorithms either focus on removing the compression artifacts at the same video resolution, or on upscaling the video resolution but not removing the artifacts. Super resolution-only approaches will amplify the artifacts along with the details by default. We propose a lightweight convolutional neural network (CNN)-based algorithm which simultaneously performs artifacts reduction and super resolution (ARSR) by enhancing the feature extraction layers and designing a custom training dataset. The output of this neural network is evaluated for test streams compressed at low bitrates using variable bitrate (VBR) encoding. The output video quality shows a 4-6 increase in video multi-method assessment fusion (VMAF) score compared to traditional interpolation upscaling approaches such as Lanczos or Bicubic. |
| title | Super Efficient Neural Network for Compression Artifacts Reduction and Super Resolution |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2401.14641 |