Implicit Neural Representation for Videos Based on Residual Connection

TL;DR

This paper introduces an implicit neural representation method for videos that leverages residual connections with low-resolution frames to enhance reconstruction quality, outperforming existing methods in PSNR on most tested videos.

Contribution

The proposed approach improves video reconstruction quality by integrating low-resolution frames as residuals within implicit neural representations, surpassing prior methods like HNeRV.

Findings

Outperforms HNeRV in PSNR for 46 out of 49 videos

Effective use of residual connections improves frame detail

Demonstrates superior reconstruction quality in experiments

Abstract

Video compression technology is essential for transmitting and storing videos. Many video compression methods reduce information in videos by removing high-frequency components and utilizing similarities between frames. Alternatively, the implicit neural representations (INRs) for videos, which use networks to represent and compress videos through model compression. A conventional method improves the quality of reconstruction by using frame features. However, the detailed representation of the frames can be improved. To improve the quality of reconstructed frames, we propose a method that uses low-resolution frames as residual connection that is considered effective for image reconstruction. Experimental results show that our method outperforms the existing method, HNeRV, in PSNR for 46 of the 49 videos.