Implicit Neural Representation for Videos Based on Residual Connection
This work addresses video compression for efficient transmission and storage, but it is incremental as it builds on existing INR methods with a specific enhancement.
The paper tackles video compression by proposing an implicit neural representation method that uses low-resolution frames as residual connections to improve reconstruction quality, achieving higher PSNR than HNeRV in 46 out of 49 videos.
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.