用光流引导提升过拟合视频编码的运动建模能力。
Improved Encoding for Overfitted Video Codecs
- 用光流估计器指导运动信息学习，改善编码精度
- 联合率失真优化使各帧码率分布更合理，提升压缩效率
- 保持每像素1300次乘法的低解码复杂度，适合实时应用
过拟合神经视频编码器的解码复杂度比自编码器低多个数量级，但压缩效率受限，部分原因在于难以准确捕捉运动信息。本文提出使用光流估计器引导运动信息学习，并引入联合率失真优化，以改善不同帧间的码率分配。这些改进在维持每像素1300次乘法的低解码复杂度的同时，压缩性能接近传统编码器HEVC，优于其他过拟合编码器。相关代码已开源：https://orange-opensource.github.io/Cool-Chic/
原文摘要 · Abstract (English)
Overfitted neural video codecs offer a decoding complexity orders of magnitude smaller than their autoencoder counterparts. Yet, this low complexity comes at the cost of limited compression efficiency, in part due to their difficulty capturing accurate motion information. This paper proposes to guide motion information learning with an optical flow estimator. A joint rate-distortion optimization is also introduced to improve rate distribution across the different frames. These contributions maintain a low decoding complexity of 1300 multiplications per pixel while offering compression performance close to the conventional codec HEVC and outperforming other overfitted codecs. This work is made open-source at https://orange-opensource.github.io/Cool-Chic/
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。