近年来，学习视频压缩引起了广泛关注，并呈现出快速发展的趋势，并取得了可喜的成果。然而，之前的工作仍然存在一些关键问题，并且在广泛使用的 PSNR 指标方面与传统压缩标准存在性能差距。在本文中，我们提出了几种有效提高性能的技术。首先，为了解决累积误差的问题，我们引入了条件 I 帧作为 GoP 中的第一帧，它可以稳定重建质量并节省比特率。其次，为了在不增加解码器复杂度的情况下有效地提高帧间预测的准确性，我们提出了一种编码器侧的像素到特征运动预测方法，帮助我们获得高质量的运动信息。第三，我们提出了一种基于概率的熵跳跃方法，不仅带来了性能增益，而且大大减少了熵编码的运行时间。借助这些强大的技术，本文提出了 AlphaVC，一种高性能且高效的学习视频压缩方案。据我们所知，AlphaVC 是第一个在 PSNR（-28.2% BD 率节省）和 MSSSIM（-52.2% BD 率节省）的所有常见测试数据集上超过最新压缩标准 VVC 的 E2E AI 编解码器，并且具有非常快的编码（0.001x VVC）和解码（1.69x VVC）速度。
Recently, learned video compression has drawn lots of attention and show a rapid development trend with promising results. However, the previous works still suffer from some criticial issues and have a performance gap with traditional compression standards in terms of widely used PSNR metric. In this paper, we propose several techniques to effectively improve the performance. First, to address the problem of accumulative error, we introduce a conditional-I-frame as the first frame in the GoP, which stabilizes the reconstructed quality and saves the bit-rate. Second, to efficiently improve the accuracy of inter prediction without increasing the complexity of decoder, we propose a pixel-to-feature motion prediction method at encoder side that helps us to obtain high-quality motion information. Third, we propose a probability-based entropy skipping method, which not only brings performance gain, but also greatly reduces the runtime of entropy coding. With these powerful techniques, this paper proposes AlphaVC, a high-performance and efficient learned video compression scheme. To the best of our knowledge, AlphaVC is the first E2E AI codec that exceeds the latest compression standard VVC on all common test datasets for both PSNR (-28.2% BD-rate saving) and MSSSIM (-52.2% BD-rate saving), and has very fast encoding (0.001x VVC) and decoding (1.69x VVC) speeds.
原文：https://arxiv.org/abs/2207.14678
Recently, learned video compression has drawn lots of attention and show a rapid development trend with promising results. However, the previous works still suffer from some criticial issues and have a performance gap with traditional compression standards in terms of widely used PSNR metric. In this paper, we propose several techniques to effectively improve the performance. First, to address the problem of accumulative error, we introduce a conditional-I-frame as the first frame in the GoP, which stabilizes the reconstructed quality and saves the bit-rate. Second, to efficiently improve the accuracy of inter prediction without increasing the complexity of decoder, we propose a pixel-to-feature motion prediction method at encoder side that helps us to obtain high-quality motion information. Third, we propose a probability-based entropy skipping method, which not only brings performance gain, but also greatly reduces the runtime of entropy coding. With these powerful techniques, this paper proposes AlphaVC, a high-performance and efficient learned video compression scheme. To the best of our knowledge, AlphaVC is the first E2E AI codec that exceeds the latest compression standard VVC on all common test datasets for both PSNR (-28.2% BD-rate saving) and MSSSIM (-52.2% BD-rate saving), and has very fast encoding (0.001x VVC) and decoding (1.69x VVC) speeds.
原文：https://arxiv.org/abs/2207.14678
