Frequency-aware Neural Representation for Videos

2026-01-25

AI Summary

This work addresses the spectral bias inherent in existing implicit neural representation (INR) methods for video compression, which favor low-frequency components and consequently produce overly smooth reconstructions with suboptimal rate-distortion performance. To mitigate this limitation, we propose FaNeRV, a novel framework that explicitly decouples high- and low-frequency components through a frequency-aware mechanism. FaNeRV incorporates a frequency-domain decomposition network, multi-resolution supervision guidance, and a dynamic high-frequency injection strategy to effectively alleviate spectral bias. Experimental results demonstrate that FaNeRV significantly outperforms current INR-based approaches on standard benchmarks, achieving rate-distortion performance comparable to conventional video codecs while enabling efficient and high-fidelity video reconstruction.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Representation Learning

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Implicit Neural Representations (INRs) have emerged as a promising paradigm for video compression. However, existing INR-based frameworks typically suffer from inherent spectral bias, which favors low-frequency components and leads to over-smoothed reconstructions and suboptimal rate-distortion performance. In this paper, we propose FaNeRV, a Frequency-aware Neural Representation for videos, which explicitly decouples low- and high-frequency components to enable efficient and faithful video reconstruction. FaNeRV introduces a multi-resolution supervision strategy that guides the network to progressively capture global structures and fine-grained textures through staged supervision . To further enhance high-frequency reconstruction, we propose a dynamic high-frequency injection mechanism that adaptively emphasizes challenging regions. In addition, we design a frequency-decomposed network module to improve feature modeling across different spectral bands. Extensive experiments on standard benchmarks demonstrate that FaNeRV significantly outperforms state-of-the-art INR methods and achieves competitive rate-distortion performance against traditional codecs.

Problem

• spectral bias
• video compression
• high-frequency reconstruction
• rate-distortion performance
• implicit neural representations

Innovation

• Frequency-aware
• Implicit Neural Representation
• Multi-resolution Supervision
• High-frequency Injection
• Video Compression