用轻量神经网络优化视频编码预测滤波，提升压缩效率
Advanced Learning-Based Inter Prediction for Future Video Coding
- 用神经网络替代传统手工滤波参数，实现高效预测
- 在RA配置下，亮度、色度分量分别提升0.01%、0.31%、0.25%编码增益
- 无需外部依赖，可直接嵌入编码器，适合实际部署
在第四代音视频编码标准（AVS4）中，帧间预测滤波器（INTERPF）用于减少预测值与邻近重建像素之间的不连续性。本文提出一种低复杂度学习型帧间预测（LLIP）方法，以替代传统INTERPF。LLIP通过轻量级神经网络增强滤波过程，其参数可导出用于高效推理。具体而言，从传统INTERPF中提取使用到的像素与坐标构建训练数据集，训练后导出网络权重与偏置，实现无第三方依赖的推理，无需Libtorch即可无缝集成至视频编解码器，从而实现更快推理速度。最终，将传统手工设计的滤波参数替换为学习得到的最优参数。实验结果表明，在随机访问（RA）配置下，该方法对Y、U、V分量平均分别获得0.01%、0.31%和0.25%的编码增益。
原文摘要 · Abstract (English)
In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.
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。