OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912045001080832 |
|---|---|
| author | Mo, Qiao Ding, Yukang Hao, Jinhua Zhu, Qiang Sun, Ming Zhou, Chao Chen, Feiyu Zhu, Shuyuan |
| author_facet | Mo, Qiao Ding, Yukang Hao, Jinhua Zhu, Qiang Sun, Ming Zhou, Chao Chen, Feiyu Zhu, Shuyuan |
| contents | Deep learning-based methods have shown remarkable performance in single JPEG artifacts removal task. However, existing methods tend to degrade on double JPEG images, which are prevalent in real-world scenarios. To address this issue, we propose Offset-Aware Partition Transformer for double JPEG artifacts removal, termed as OAPT. We conduct an analysis of double JPEG compression that results in up to four patterns within each 8x8 block and design our model to cluster the similar patterns to remedy the difficulty of restoration. Our OAPT consists of two components: compression offset predictor and image reconstructor. Specifically, the predictor estimates pixel offsets between the first and second compression, which are then utilized to divide different patterns. The reconstructor is mainly based on several Hybrid Partition Attention Blocks (HPAB), combining vanilla window-based self-attention and sparse attention for clustered pattern features. Extensive experiments demonstrate that OAPT outperforms the state-of-the-art method by more than 0.16dB in double JPEG image restoration task. Moreover, without increasing any computation cost, the pattern clustering module in HPAB can serve as a plugin to enhance other transformer-based image restoration methods. The code will be available at https://github.com/QMoQ/OAPT.git . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal Mo, Qiao Ding, Yukang Hao, Jinhua Zhu, Qiang Sun, Ming Zhou, Chao Chen, Feiyu Zhu, Shuyuan Image and Video Processing Computer Vision and Pattern Recognition Deep learning-based methods have shown remarkable performance in single JPEG artifacts removal task. However, existing methods tend to degrade on double JPEG images, which are prevalent in real-world scenarios. To address this issue, we propose Offset-Aware Partition Transformer for double JPEG artifacts removal, termed as OAPT. We conduct an analysis of double JPEG compression that results in up to four patterns within each 8x8 block and design our model to cluster the similar patterns to remedy the difficulty of restoration. Our OAPT consists of two components: compression offset predictor and image reconstructor. Specifically, the predictor estimates pixel offsets between the first and second compression, which are then utilized to divide different patterns. The reconstructor is mainly based on several Hybrid Partition Attention Blocks (HPAB), combining vanilla window-based self-attention and sparse attention for clustered pattern features. Extensive experiments demonstrate that OAPT outperforms the state-of-the-art method by more than 0.16dB in double JPEG image restoration task. Moreover, without increasing any computation cost, the pattern clustering module in HPAB can serve as a plugin to enhance other transformer-based image restoration methods. The code will be available at https://github.com/QMoQ/OAPT.git . |
| title | OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.11480 |