Corpus ID: 214713520

BVI-DVC: A Training Database for Deep Video Compression

@article{Ma2020BVIDVCAT,
  title={BVI-DVC: A Training Database for Deep Video Compression},
  author={Di Ma and Fangfang Zhang and David R. Bull},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.13552}
}
  • Di Ma, Fangfang Zhang, David R. Bull
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches. Such approaches often employ Convolutional Neural Networks (CNNs) which are trained on databases with relatively limited content coverage. In this paper, a new extensive and representative video database, BVI-DVC, is presented for training CNN-based coding tools. BVI-DVC contains 800 sequences at… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 78 REFERENCES

    Enhanced Video Compression Based on Effective Bit Depth Adaptation

    VIEW 1 EXCERPT

    Image and Video Compression With Neural Networks: A Review

    VIEW 1 EXCERPT

    Convolutional Neural Network-Based Block Up-Sampling for HEVC

    VIEW 2 EXCERPTS

    Enhanced Bi-Prediction With Convolutional Neural Network for High-Efficiency Video Coding

    VIEW 1 EXCERPT

    Dense Residual Convolutional Neural Network based In-Loop Filter for HEVC

    VIEW 1 EXCERPT

    Perceptually-inspired super-resolution of compressed videos

    VIEW 1 EXCERPT

    Video Compression Based on Spatio-Temporal Resolution Adaptation

    VIEW 9 EXCERPTS

    Deep Learning-Based Video Coding

    VIEW 1 EXCERPT