Abstract: The present embodiment provides an image restoration method and apparatus which generate independent different restoration models by performing learning for each of different resolutions, receive a distorted image, and apply a restoration model corresponding to the resolution of the distorted image among the independent different restoration models to restore the distorted image into an improved upscaled image centering on a restoration target object within the distorted image.

Abstract: The apparatus includes a video signal acquisition device, an audio signal acquisition device, a time information processing device, a video signal encoding device, an audio signal encoding device, a multiplexing device and an output device. The video signal acquisition device receives the video signals and converts them into digital video data. The audio signal acquisition device receives the audio signals and converts them into digital audio data. The time information processing device receives a clock signal for synchronization of the digital video and audio data. The video signal encoding device encodes the digital video data. The audio signal encoding device encodes the audio video data. The multiplexing device converts the encoded video and audio signals into a single piece of bit stream data. The output device outputs the bit stream data. The time information processing device provides the two pieces of time information respectively as a video reference clock and an audio reference clock.