Light Field Compression Based on Implicit Neural Representation

TL;DR

This paper introduces a novel light field compression method using implicit neural representations, effectively reducing data redundancy and achieving high-quality results comparable to traditional techniques.

Contribution

The paper presents a new neural network-based approach for light field compression that implicitly encodes multi-view information, improving efficiency over classical methods.

Findings

Achieves comparable rate-distortion performance to traditional methods.

Provides superior perceptual quality in reconstructed light fields.

Effectively reduces data redundancy between views.

Abstract

Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.