Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames

TL;DR

This paper introduces a frequency-domain deep learning model for MPEG I-frame quality enhancement by predicting missing DCT coefficients, significantly improving video quality at low bitrates.

Contribution

It presents a novel frequency-to-frequency domain approach for video quality enhancement using deep learning to predict quantized DCT coefficients in MPEG I-frames.

Findings

Improved video quality from QF 10 to near QF 20.

Effective frequency domain deep learning model for DCT coefficient prediction.

Demonstrated enhancement in low-quality MPEG I-frames.

Abstract

Recent works have successfully applied some types of Convolutional Neural Networks (CNNs) to reduce the noticeable distortion resulting from the lossy JPEG/MPEG compression technique. Most of them are built upon the processing made on the spatial domain. In this work, we propose a MPEG video decoder that is purely based on the frequency-to-frequency domain: it reads the quantized DCT coefficients received from a low-quality I-frames bitstream and, using a deep learning-based model, predicts the missing coefficients in order to recompose the same frames with enhanced quality. In experiments with a video dataset, our best model was able to improve from frames with quantized DCT coefficients corresponding to a Quality Factor (QF) of 10 to enhanced quality frames with QF slightly near to 20.