Versatile Learned Video Compression
Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the prediction mode and the fixed network framework. They are unable to support various inter prediction modes and thus inapplicable for various scenarios. In this paper, to break this limitation, we propose a versatile learned video compression (VLVC) framework that uses one model to support all possible prediction modes. Specifically, to realize versatile compression, we first build a motion compensation module that applies multiple 3D motion vector fields (i.e., voxel flows) for weighted trilinear warping in spatial-temporal space. The voxel flows convey the information of temporal reference position that helps to decouple inter prediction modes away from framework designing. Secondly, in case of multiple-reference-frame prediction, we apply a flow prediction module to predict accurate motion trajectories with unified polynomial functions. We show that the flow prediction module can largely reduce the transmission cost of voxel flows. Experimental results demonstrate that our proposed VLVC not only supports versatile compression in various settings, but also is the first end-to-end learned video compression method that outperforms the latest VVC/H.266 standard reference software in terms of MS-SSIM.
Code (0)
등록된 구현이 없습니다.
Tasks
Motion CompensationMS-SSIMPredictionSSIMVideo CompressionSimilar Papers 제목 키워드 기반
Coding Standards as Anchors for the CVPR CLIC video track
In 2021, a new track has been initiated in the Challenge for Learned Image Compression~: the video track. This category proposes to explore technologies for the compression of short video clips at 1 Mbit/s. This paper pr…
Image CompressionLearned Image Coding for Machines: A Content-Adaptive Approach
Today, according to the Cisco Annual Internet Report (2018-2023), the fastest-growing category of Internet traffic is machine-to-machine communication. In particular, machine-to-machine communication of images and videos…
Data CompressionImage CompressionLearned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising resu…
Image CompressionMS-SSIMSSIMEnhanced Invertible Encoding for Learned Image Compression
Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most o…
Image CompressionInterpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding
Deep learning has shown great potential in image and video compression tasks. However, it brings bit savings at the cost of significant increases in coding complexity, which limits its potential for implementation within…
Motion CompensationVideo Compression