Restoring high-quality videos from the compressed ones is a crucial research topic in video coding. Most existing methods generally take the raw video as the ground truth to guide the reconstruction. We find that the compressed frames contain less texture details than the raw frames, which we called valid information. As shown in Figure 1 , we propose a Valid Information Guidance (VIG) scheme to recover the raw spatio-temporal distribution via making full use of valid information. Specifically, we propose a Truth Guidance Distillation (TGD) strategy to learn to model the spatio-temporal correspondence from the rich valid information contained in the raw frames. We replace ninety percent of the compressed blocks with the raw blocks for pre-training. Furthermore, we propose an efficient Compressed Redundancy Filtering (CRF) network to extract valid information by filtering the compressed frames.

Restoring high-quality videos from low-quality compressed ones is a crucial research topic in video coding. Most existing methods do not exploit the information in the long-distance compressed frames. Even when they do, these methods ignore the effect of interference information during reconstruction. As shown in Figure 1, we propose a unique Long-distance Information Filtering (LIF) scheme with the 3D-CNN, which enhances compressed videos by mining filtered and valid information from long-distance frames. Specifically, we propose a practical block, Long-distance Feature Extraction (LFE) block, to model the spatio-temporal relationship within a long temporal range. Furthermore, a progressive Information Filtering (IF) module is proposed in LFE to promote artifact removal and texture restoration by capturing a large effective receptive field, which can significantly boost the effect of LIF. We use MFQE 2.0 dataset for training and compare LIF to the following novel VQE methods on 18 standard test sequences of Joint Collaborative Team on Video Coding (JCT-VC) as the test set in Table 1. Extensive experiments demonstrate that our method achieves state-of-the-art performance with nearly 25% of the parameters and half of the training volume, which indicates that our model is more lightweight and more efficient.