IVCVAug 21, 2024

OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal

arXiv:2408.11480v24 citationsh-index: 9Has Code
Originality Highly original
AI Analysis

This addresses a real-world issue in image restoration for applications dealing with double-compressed JPEG images, representing an incremental improvement with a novel method for a known bottleneck.

The paper tackles the problem of double JPEG artifacts removal, which degrades existing methods, by proposing OAPT, an Offset-Aware Partition Transformer that clusters compression patterns and achieves a performance gain of over 0.16dB over state-of-the-art methods.

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 .

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes