VQ-NeRV: A Vector Quantized Neural Representation for Videos

TL;DR

VQ-NeRV introduces a vector quantized neural architecture with a novel codebook mechanism and optimization for improved video compression and reconstruction, outperforming previous methods like HNeRV in quality and efficiency.

Contribution

The paper proposes VQ-NeRV, a U-shaped neural architecture with a codebook for discretizing residual features, enhancing video compression and reconstruction capabilities.

Findings

VQ-NeRV achieves 1-2 dB higher PSNR than HNeRV.

VQ-NeRV uses less bits per pixel, improving compression.

VQ-NeRV improves video inpainting results.

Abstract

Implicit neural representations (INR) excel in encoding videos within neural networks, showcasing promise in computer vision tasks like video compression and denoising. INR-based approaches reconstruct video frames from content-agnostic embeddings, which hampers their efficacy in video frame regression and restricts their generalization ability for video interpolation. To address these deficiencies, Hybrid Neural Representation for Videos (HNeRV) was introduced with content-adaptive embeddings. Nevertheless, HNeRV's compression ratios remain relatively low, attributable to an oversight in leveraging the network's shallow features and inter-frame residual information. In this work, we introduce an advanced U-shaped architecture, Vector Quantized-NeRV (VQ-NeRV), which integrates a novel component--the VQ-NeRV Block. This block incorporates a codebook mechanism to discretize the network's shallow residual features and inter-frame residual information effectively. This approach proves particularly advantageous in video compression, as it results in smaller size compared to quantized features. Furthermore, we introduce an original codebook optimization technique, termed shallow codebook optimization, designed to refine the utility and efficiency of the codebook. The experimental evaluations indicate that VQ-NeRV outperforms HNeRV on video regression tasks, delivering superior reconstruction quality (with an increase of 1-2 dB in Peak Signal-to-Noise Ratio (PSNR)), better bit per pixel (bpp) efficiency, and improved video inpainting outcomes.