标题： 过拟合视频编解码器的改进编码方法 显示英文标题

标题： Improved Encoding for Overfitted Video Codecs

摘要： 过拟合的神经网络视频编解码器提供的解码复杂度比其自编码器对应物小几个数量级。然而，这种低复杂度是以压缩效率有限为代价的，部分原因是它们难以捕捉准确的运动信息。本文提出使用光流估计算子来引导运动信息的学习。此外，还引入了联合率失真优化以改善不同帧之间的率分布。这些贡献在每个像素的解码复杂度保持在1300次乘法的同时，提供了接近传统编解码器HEVC的压缩性能，并且优于其他过拟合编解码器。本工作已在https://orange-opensource.github.io/Cool-Chic/开源。 显示英文摘要

摘要： 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/