Methods for decoding and encoding video signals, video signal encoders / decoders, and computer-readable, invariant materials

Abstract

The invention relates to the field of image or video compression technology based on artificial intelligence (AI), and relates to methods and apparatus for encoding and decoding video signals. The video signal encoding method includes the following steps: providing the control signal of the first signal component of the video signal to the first feature map of the first signal component, in order to receive the second feature map of the first signal component, where the control signal of the first signal component is received through learning; The control signal of the second signal component of the micro-signal is fed to the first feature map of the second signal component, to receive the second feature map of the second signal component, in which the control signal of the second signal component is received through learning; and the bit stream of the micro-signal is received based on the second feature map of the first signal component and the second feature map of the second signal component. The invention is compatible with image content that has different color characteristics.