While learned video codecs have demonstrated great promise, they have yet to achieve sufficient efficiency for practical deployment. In this work, we propose several novel ideas for learned video compression which allow for improved performance for the low-latency mode (I- and P-frames only) along with a considerable increase in computational efficiency. In this setting, for natural videos our approach compares favorably across the entire R-D curve under metrics PSNR, MS-SSIM and VMAF against all mainstream video standards (H.264, H.265, AV1) and all ML codecs. At the same time, our approach runs at least 5x faster and has fewer parameters than all ML codecs which report these figures. Our contributions include a flexible-rate framework allowing a single model to cover a large and dense range of bitrates, at a negligible increase in computation and parameter count; an efficient backbone optimized for ML-based codecs; and a novel in-loop flow prediction scheme which leverages prior information towards more efficient compression. We benchmark our method, which we call ELF-VC (Efficient, Learned and Flexible Video Coding) on popular video test sets UVG and MCL-JCV under metrics PSNR, MS-SSIM and VMAF. For example, on UVG under PSNR, it reduces the BD-rate by 44% against H.264, 26% against H.265, 15% against AV1, and 35% against the current best ML codec. At the same time, on an NVIDIA Titan V GPU our approach encodes/decodes VGA at 49/91 FPS, HD 720 at 19/35 FPS, and HD 1080 at 10/18 FPS.
翻译:虽然所学的视频代码已经显示出巨大的希望,但是它们还没有达到用于实际部署的充分效率。 在这项工作中,我们提出一些新颖的视频压缩方法,以便提高低延迟模式(仅I-和P-框架)的性能,同时大幅提高计算效率。在这一背景下,在自然视频方面,我们的方法在PSNR、MS-SSIM和VMAF等标准下在整个R-D曲线中与所有主流视频标准(H.264、H.265、AV1)和所有ML代码相比,都表现出巨大的希望。与此同时,我们的方法至少运行了5x速度,比报告这些数字的所有ML代码的参数要少。我们的贡献包括一个灵活的框架,允许一个单一模型覆盖大量和密集的比特率,计算和参数数略有增加;一个高效的骨架为MLCS、MSIM、MV-MG等标准优化;以及一个将先前的信息用于更高效的流程预测方案。我们用ELF-VC、44-VS、CRV-MG等当前视频和MVG的频率测试方法,我们在PV-B-C、V-B-B-C、V-C、V-PLV-C、V-C、V-C、V-C、PLV-C、VLV-C、V-C、V-C、V-RM-C、V-C、V-C、V-C、IB-C、B-C、V-C、V-C、V-C、VLB-C、B-C、V-B-C、B-C、B-C、B-C-C、B-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-B-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-B-