Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
This work improves video quality enhancement for heavily compressed videos, but it is incremental as it builds on existing multi-frame approaches.
The paper tackles video compression artifact reduction by proposing a reference frame proposal strategy and a frequency domain loss, achieving state-of-the-art fidelity and perceptual performance on the MFQE 2.0 dataset and winning top ranks in the NTIRE 2021 challenge.
Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos. Recently, methods were proposed to mine spatiotemporal information via utilizing multiple neighboring frames as reference frames. However, these post-processing methods take advantage of adjacent frames directly, but neglect the information of the video itself, which can be exploited. In this paper, we propose an effective reference frame proposal strategy to boost the performance of the existing multi-frame approaches. Besides, we introduce a loss based on fast Fourier transformation~(FFT) to further improve the effectiveness of restoration. Experimental results show that our method achieves better fidelity and perceptual performance on MFQE 2.0 dataset than the state-of-the-art methods. And our method won Track 1 and Track 2, and was ranked the 2nd in Track 3 of NTIRE 2021 Quality enhancement of heavily compressed videos Challenge.