Brand F, Seiler J, Kaup A (2019)
Publication Type: Conference contribution, Conference Contribution
Publication year: 2019
Intra prediction is a vital component of most modern
image and video codecs. State of the art video codecs like High
Efficiency Video Coding (HEVC) or the upcoming Versatile Video
Coding (VVC) use a high number of directional modes. With the
recent advances in deep learning, it is now possible to use artificial
neural networks for intra frame prediction. Previously published
approaches usually add additional ANN based modes or replace
all modes by training several networks. In our approach, we
use a single autoencoder network to first compress the original
with help of already transmitted pixels to four parameters.
We then use the parameters together with this support area
to generate a prediction for the block. This way, we are able
to replace all angular intra modes by a single ANN. In the
experiments we compare our method with the intra prediction
method currently used in the VVC Test Model (VTM). Using
our method, we are able to gain up to 0.85 dB prediction PSNR
with a comparable amount of side information or reduce the
amount of side information by 2 bit per prediction unit with
Brand, F., Seiler, J., & Kaup, A. (2019). Intra Frame Prediction for Video Coding Using a Conditional Autoencoder Approach. In Proceedings of the Picture Coding Symposium (PCS). Ningbo, CN.
Brand, Fabian, Jürgen Seiler, and André Kaup. "Intra Frame Prediction for Video Coding Using a Conditional Autoencoder Approach." Proceedings of the Picture Coding Symposium (PCS), Ningbo 2019.