自适应高频预处理让视频更清晰且省带宽
Adaptive High-Frequency Preprocessing for Video Coding
- 用神经网络动态选择最优高频处理策略
- 在多个数据集上实现显著画质提升与码率降低
- 适合需要高效编码的视频应用开发者
高频分量对维持视频清晰度和真实感至关重要，但也会显著增加编码码率，导致带宽和存储成本上升。本文提出一种端到端学习框架，实现自适应高频预处理，以提升主观画质并节省码率。该框架采用频率感知特征金字塔预测网络（FFPN）预测最优高频预处理策略，指导后续滤波操作，在压缩后实现码率与质量的最佳权衡。训练时，通过对比不同预处理类型和强度的率失真（RD）性能，为每个训练视频伪标注最优策略。失真使用最新的质量评估指标进行测量。在多个数据集上的全面评估表明，该框架具有出色的视觉增强能力和码率节省效果。
原文摘要 · Abstract (English)
High-frequency components are crucial for maintaining video clarity and realism, but they also significantly impact coding bitrate, resulting in increased bandwidth and storage costs. This paper presents an end-to-end learning-based framework for adaptive high-frequency preprocessing to enhance subjective quality and save bitrate in video coding. The framework employs the Frequency-attentive Feature pyramid Prediction Network (FFPN) to predict the optimal high-frequency preprocessing strategy, guiding subsequent filtering operators to achieve the optimal tradeoff between bitrate and quality after compression. For training FFPN, we pseudo-label each training video with the optimal strategy, determined by comparing the rate-distortion (RD) performance across different preprocessing types and strengths. Distortion is measured using the latest quality assessment metric. Comprehensive evaluations on multiple datasets demonstrate the visually appealing enhancement capabilities and bitrate savings achieved by our framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。