# A DenseNet Based Approach for Multi-Frame In-Loop Filter in HEVC

## TL;DR

This paper introduces a DenseNet-based multi-frame in-loop filter for HEVC that leverages neighboring frames to improve video quality, outperforming existing methods in efficiency and effectiveness.

## Contribution

It presents a novel multi-frame in-loop filtering approach using DenseNet, enhancing HEVC compression quality by utilizing spatial and temporal information from multiple frames.

## Key findings

- Outperforms HM baseline in quality metrics
- Improves compression efficiency over state-of-the-art methods
- Demonstrates better generalization and computational efficiency

## Abstract

High efficiency video coding (HEVC) has brought outperforming efficiency for video compression. To reduce the compression artifacts of HEVC, we propose a DenseNet based approach as the in-loop filter of HEVC, which leverages multiple adjacent frames to enhance the quality of each encoded frame. Specifically, the higher-quality frames are found by a reference frame selector (RFS). Then, a deep neural network for multi-frame in-loop filter (named MIF-Net) is developed to enhance the quality of each encoded frame by utilizing the spatial information of this frame and the temporal information of its neighboring higher-quality frames. The MIF-Net is built on the recently developed DenseNet, benefiting from the improved generalization capacity and computational efficiency. Finally, experimental results verify the effectiveness of our multi-frame in-loop filter, outperforming the HM baseline and other state-of-the-art approaches.