PNeRV: A Polynomial Neural Representation for Videos

TL;DR

PNeRV introduces a novel polynomial neural network-based implicit representation for videos that maintains spatiotemporal continuity, improving compression and analysis tasks over traditional frame-only INRs.

Contribution

The paper proposes PNeRV, a parameter-efficient, patch-wise INR for videos utilizing polynomial neural networks and a hierarchical sampling scheme to preserve spatiotemporal continuity.

Findings

Outperforms baseline INRs in video compression tasks.

Enhances downstream video processing applications.

Addresses challenges of temporal modeling in video INRs.

Abstract

Extracting Implicit Neural Representations (INRs) on video data poses unique challenges due to the additional temporal dimension. In the context of videos, INRs have predominantly relied on a frame-only parameterization, which sacrifices the spatiotemporal continuity observed in pixel-level (spatial) representations. To mitigate this, we introduce Polynomial Neural Representation for Videos (PNeRV), a parameter-wise efficient, patch-wise INR for videos that preserves spatiotemporal continuity. PNeRV leverages the modeling capabilities of Polynomial Neural Networks to perform the modulation of a continuous spatial (patch) signal with a continuous time (frame) signal. We further propose a custom Hierarchical Patch-wise Spatial Sampling Scheme that ensures spatial continuity while retaining parameter efficiency. We also employ a carefully designed Positional Embedding methodology to further enhance PNeRV's performance. Our extensive experimentation demonstrates that PNeRV outperforms the baselines in conventional Implicit Neural Representation tasks like compression along with downstream applications that require spatiotemporal continuity in the underlying representation. PNeRV not only addresses the challenges posed by video data in the realm of INRs but also opens new avenues for advanced video processing and analysis.