Back to Search
Document details
EE1-3.1: Neural network-based intra prediction with reduced complexity
Abstract
Following the 29th JVET meeting, three additional neural network-based coding tools, see JVET-AC0055, JVET-AC0196, and JVET-AC0116, were integrated into VTM-11-NNVC. In JVET-AC0116, a neural network-based intra prediction mode is added to the set of intra prediction modes in VTM-11-NNVC. To limit the complexity of the neural network-based intra prediction mode, each neural network in this mode features a relatively small architecture and weight sparsity is enforced. However, the architecture and weight sparsity policy are not tuned to each neural network.
JVET-AF0139 EE1-3.1: neural network-based intra prediction with reduced complexity [T. Dumas, F. Galpin, P. Bordes (InterDigital)]
See JVET-AF0023.
Cited:
ARCHIVE
:
ee1_3dot1_training_large_nnintrapred_1_nnlfoption_0_vs_nnvc_6_nnintrapred_0_nnlfoption_0.xlsm
ee1_3dot1_training_large_nnintrapred_1_nnlfoption_3_vs_nnvc_6_nnintrapred_1_nnlfoption_3.xlsm
ee1_3dot1_training_small_nnintrapred_1_nnlfoption_0_vs_nnvc_6_nnintrapred_0_nnlfoption_0.xlsm
ee1_3dot1_training_small_nnintrapred_1_nnlfoption_3_vs_nnvc_6_nnintrapred_1_nnlfoption_3.xlsm
JVET-AF0139-v2.docx
Decisions
See JVET-AF0023.
Citation