Fast CU partition-based machine learning approach for reducing HEVC complexity

Introduction to the special issue on deep learning for real-time information hiding and forensics

“…HEVC complexity", is co-authored by Bouaafia et al [19]. In this paper, two machine learning-based fast CU partition methods for inter-mode HEVC are proposed, in order to optimize the complexity allocation at CU level.…”

A Deep CNN-LSTM Framework for Fast Video Coding

“…A large-scale database for CU partition of the inter-mode HEVC was established, to train the proposed model, as shown in [12]. However, to construct the database, we selected 114 video sequences with various resolutions (from 352 × 240 to 2560 × 1600) [15,16].…”

“…The proposed LSTM network learns the long and short-term dependencies of the CU partition across frames. In our previous proposed method [12], all parameters of Deep CNN are trained over the residual CTU and the ground-truth splitting of the CTUs, then the extracted features (F C 1−l ) 3 l=1 of Deep CNN are the input of LSTM network at frame t. These features (F C 1−l ) 3 l=1 are extracted at the first fully connected layer of Deep CNN [12]. The proposed algorithm that combines CNN and LSTM is shown in Fig.…”

“…Based on our previous work presented in [12], our deep CNN structure has been proposed to predict the CU splitting in order to reduce the coding performance of inter-mode HEVC. A large-scale training database was established in [12].…”

“…Based on our previous work presented in [12], our deep CNN structure has been proposed to predict the CU splitting in order to reduce the coding performance of inter-mode HEVC. A large-scale training database was established in [12]. Therefore, to predict the inter-mode CU partition, this paper proposes a CNN-LSTM-based learning approach where the aim is to reduce the HEVC complexity in terms of RD performance and encoding time.…”