Page 53 - ITU Journal, ICT Discoveries, Volume 3, No. 1, June 2020 Special issue: The future of video and immersive media

ITU Journal: ICT Discoveries, Vol. 3(1), June 2020

subband decomposition were employed. In this way, one [15] D. Kingma, J. Ba (2015), Adam: A Method for Stochas-
could significantly decrease the complexity of the predic- tic Optimization, in Int. Conf. on Learning Representa-
tors and finally make them suitable for a broad applica- tions, 2014
tion scenario like versatile video coding.
[16] J. Li, B. Li, J. Xu, R. Xiong, W. Gao, Fully Connected
Network-Based Intra prediction for Image Coding, in
REFERENCES
IEEE Trans. Image Process, vol. 27, no. 7, 2018, pp.
[1] E. Agustsson, F. Mentzer, M. Tschannen, L. Cavigelli, R. 3236-3247
Timofte, L. Benini, and L. V. Gool, Soft-to-hard vector
quantizationforend-to-endlearningcompressiblerep- [17] D. Minnen, J. Ballé, G. Toderici, Joint autoregressive
resentations, in Advances in Neural Information Pro- and hierarchical priors for learned image compression,
cessing Systems, 2017 in Advances in Neural Information Processing Systems,
2018
[2] M. Albrecht et al., Description of SDR, HDR and 360 °
video coding technology proposal by Fraunhofer HHI, [18] F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte,
Doc. JVET-J0014, San Diego, 2018 and L. V. Gool, Conditional probability models for deep
image compression, in IEEE Conf. on Computer Vision
[3] J. Ballé, V. Laparra, E. P. Simoncelli, End-to-end op- and Pattern Recognition, 2018.
timized image compression, in Int. Conf. on Learning
Representations, 2017 [19] G. J. Sullivan, J.-R. Ohm, Meeting Report of the 10th
JVET Meeting, Doc. JVET-J1000, San Diego, 2018
[4] J. Ballé, D. Minnen, S. Singh, S. J. Hwang, and N. John-
ston, Variational image compression with a scale hy- [20] J. Pfaff, H. Schwarz, D. Marpe, B. Bross, S. De-Luxán-
perprior, in Int. Conf. on Learning Representations, Hernández, P. Helle, C. R. Helmrich, T. Hinz, W.-Q. Lim,
2018 J. Ma, T. Nguyen, J. Rasch, M. Schäfer, M. Siekmann,
G. Venugopal, A. Wieckowski, M. Winken, T. Wiegand
[5] G. Bjøntegaard, Calculation of average PSNR differ-
Video Compression Using Generalized Binary Parti-
ences between RD-curves, Doc. VCEG-M33, 2001
tioning, Trellis Coded Quantization, Perceptually Opti-
[6] G. Bjøntegaard, Improvement of BD-PSNR Model, Doc. mized Encoding, and Advanced Prediction and Trans-
VCEG-AI11, 2008 form Coding , to appear in IEEE Trans. Circuits and Sys-
tems for Video Technol.
[7] F. Bossen, J. Boyce, X. Li, V. Seregin, K. Sühring, JVET
common test conditions and software reference con- [21] J. Pfaff, P. Helle, D. Maniry and S. Kaltenstadler, B.
figurations for SDR video, Doc. JVET-N1010, Geneva, Stallenberger, P. Merkle, M. Siekmann, H. Schwarz, D.
2019 Marpe, T. Wiegand, Intra prediction modes based on
Neural Networks, Doc. JVET-J0037, San Diego, 2018
[8] B. Bross, Versatile Video Coding (Draft 1), Doc. JVET-
J1001, San Diego, 2018 [22] J. Pfaff, P. Helle, D. Maniry, S. Kaltenstadler, W. Samek,
H. Schwarz, D. Marpe, T. Wiegand, Neural network
[9] B. Bross, J. Chen, S. Liu, Versatile Video Coding (Draft based intra prediction for video coding, in Proc. SPIE
5), Doc. JVET-N1001, Geneva, 2019 Applic. of Digital Image Process. XLI, volume 10752,
2018
[10] B. Bross, J. Chen, S. Liu, Versatile Video Coding (Draft
8), Doc. JVET-Q2001, Brussels, 2020
[23] J. Pfaff, B. Stallenberger, M. Schäfer, P. Merkle, P.
[11] J. Chen, M. Karczewicz, Y.-W. Huang, K. Choi, J.-R. Helle, T. Hinz, H. Schwarz, D. Marpe, T. Wiegand, CE3:
Ohm, G. J. Sullivan, The Joint Exploration Model (JEM) Affine linear weighted intra prediction (CE3-4.1, CE3-
for Video Compression with Capability beyond HEVC, to 4.2), Doc. JVET-N0217, Geneva, 2019
appear in IEEE Trans. Circuits and Systems for Video
[24] O. Rippel, L. Bourdev, Real-time adaptive image com-
Technol.
pression, in Proc. of Machine Learning Research, vol.
[12] ITU-T and ISO/IEC, Advanced Video Coding for 70, 2017, pp. 2922–2930
Generic Audiovisual Services, H.264 and ISO/IEC
[25] A. Said, X. Zhao, M. Karczewicz, J. Chen, Position de-
14496-10, vers. 1, 2003
pendent prediction combination for intra-frame video
[13] ITU-T and ISO/IEC, High Efficiency Video Coding, coding, in IEEE International Conference on Image
H.265 and ISO/IEC 23008-2, vers. 1, 2013 Processing (ICIP), 2016
[14] P. Helle, J. Pfaff, M. Schäfer, R. Rischke, H. Schwarz, D. [26] M. Schäfer, B. Stallenberger, J. Pfaff, P. Helle, H.
Marpe, T. Wiegand, Intra Picture Prediction for Video Schwarz, D. Marpe, T. Wiegand An Affine-Linear intra
Coding with Neural Networks, in Proc. IEEE Data Com- prediction With Complexity Constraints , in IEEE Inter-
pression Conf. (DCC), Snowbird, 2019 national Conference on Image Processing (ICIP), 2019

© International Telecommunication Union, 2020 31