CVAIIVNov 11, 2024

High-Frequency Enhanced Hybrid Neural Representation for Video Compression

arXiv:2411.06685v22 citationsh-index: 33Expert syst appl
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in neural video compression for applications requiring high-quality video reconstruction.

The paper tackles the problem of neural video representations lacking high-frequency details by introducing a high-frequency enhanced hybrid neural representation network, which improves detail preservation and compression performance on Bunny and UVG datasets.

Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing work overlooks the crucial issue that videos reconstructed by these methods lack high-frequency details. To address this problem, this paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network. Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network. Specifically, we design a wavelet high-frequency encoder that incorporates Wavelet Frequency Decomposer (WFD) blocks to generate high-frequency feature embeddings. Next, we design the High-Frequency Feature Modulation (HFM) block, which leverages the extracted high-frequency embeddings to enhance the fitting process of the decoder. Finally, with the refined Harmonic decoder block and a Dynamic Weighted Frequency Loss, we further reduce the potential loss of high-frequency information. Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods, showing notable improvements in detail preservation and compression performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes