逆转损伤：一种面向编解码压缩下8K视频复原的QP感知Transformer-Diffusion方法
Reversing the Damage: A QP-Aware Transformer-Diffusion Approach for 8K Video Restoration under Codec Compression
AI总结：
本文提出DiQP模型，首次在不引入额外噪声的条件下利用去噪扩散复原AV1/HEVC编解码压缩伪影，并结合Transformer与窗口化时空机制及前后帧辅助模块，在4K和8K视频复原上优于现有方法。
摘要：
本文提出DiQP，一种用于恢复因编解码压缩而降质的8K视频质量的新型Transformer-Diffusion模型。据我们所知，该模型是首个在不考虑额外噪声的情况下，通过去噪扩散来恢复各种编解码器（AV1、HEVC）所引入伪影的方法。该方法使我们能够对压缩伪影复杂的非高斯特性进行建模，从而有效地学习逆转降质过程。我们的架构结合了Transformer捕捉长程依赖关系的能力与一种增强的窗口化机制，该机制在跨帧的像素组内保持时空上下文。为进一步提升复原效果，该模型引入了辅助的“向前看”（Look Ahead）和“环顾四周”（Look Around）模块，提供未来帧和周围帧信息，以帮助重建精细细节并提升整体视觉质量。在不同数据集上的大量实验表明，我们的模型优于最先进的方法，尤其对于4K和8K等高分辨率视频，展示了其从高度压缩源中恢复感知愉悦视频的有效性。
英文摘要：
In this paper, we introduce DiQP; a novel Transformer-Diffusion model for restoring 8K video quality degraded by codec compression. To the best of our knowledge, our model is the first to consider restoring the artifacts introduced by various codecs (AV1, HEVC) by Denoising Diffusion without considering additional noise. This approach allows us to model the complex, non-Gaussian nature of compression artifacts, effectively learning to reverse the degradation. Our architecture combines the power of Transformers to capture long-range dependencies with an enhanced windowed mechanism that preserves spatiotemporal context within groups of pixels across frames. To further enhance restoration, the model incorporates auxiliary "Look Ahead" and "Look Around" modules, providing both future and surrounding frame information to aid in reconstructing fine details and enhancing overall visual quality. Extensive experiments on different datasets demonstrate that our model outperforms state-of-the-art methods, particularly for high-resolution videos such as 4K and 8K, showcasing its effectiveness in restoring perceptually pleasing videos from highly compressed sources.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
