Deep Contextual Video Compression

By Jiahao Li, Bin Li, Yan Lu. Neural Information Processing Systems, 2021

468 citations recorded by the source corpus.

Most of the existing neural video compression methods adopt the predictive coding framework, which first generates the predicted frame and then encodes its residue with the current frame. However, as for compression ratio, predictive coding is only a sub-optimal solution as it uses simple subtraction operation to remove the redundancy across frames. In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding. In particular, we try to answer the following questions: how to define, use, and learn condition under a deep video compression framework. To tap the potential of conditional coding, we propose using feature domain context as condition. This enables us to leverage the high dimension context to carry rich information to both the encoder and the decoder, which helps reconstruct the high-frequency contents for higher video quality. Our framework is also extensible, in which the condition can be flexibly designed. Experiments show that our method can significantly outperform the previous state-of-the-art (SOTA) deep video compression methods. When compared with x265 using veryslow preset, we can achieve 26.0% bitrate saving for 1080P standard test videos.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/817dc4a2be7356027a5b7b577de01e7310fc2027

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Yan Lu
2. Bin Li
3. Jiahao Li
4. Kailin Tan
5. Sixian Wang
6. Ping Zhang
7. Zhongwei Si
8. Jincheng Dai

Citations in the corpus

• Nonlinear Transform Source-Channel Coding for Semantic Communications (2021, methodology): “As an emerging lossy compression model [19]–[23], NTC imitates the classical source coding procedure, that operates on a simple principle: a source vector x is not mapped to codeword vector directly, rather, an alterative latent representation of x is found first, a vector in some other space y, qua”
• Neural Video Compression with Diverse Contexts (2023, methodology): “As for the NVC benchmarks, we compare with the recent SOTA models including CANF-VC [21], DCVC [28], DCVC-TCM [50], and DCVC-HEM [29].”