VQ-NeRV: A Vector Quantized Neural Representation for Videos

arXiv:2403.12401v1 Announce Type: new
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 …

abstract arxiv compression computer computer vision cs.cv denoising embeddings encoding excel implicit neural representations networks neural networks regression representation tasks type vector video video compression videos vision