AMF-VSN: Adaptive multi-process fusion video steganography based on invertible neural networks

Yangwen Zhang, Yuling Chen, Hui Dou, Yan Meng, Haojin Zhu

Abstract: Highlights•Design the MCSPDense Block and flexible balance adjustment factor to flexibly balance the number of model parameters and the quality of the generated stego video.•Design Simple Redundancy Prediction Module (SRPM), improve model performance while reducing the number of model parameters.•Design HQR mode and SC mode to meet the needs of different application scenarios.