Improved Positional Encoding for Implicit Neural Representation based Compact Data Representation

TL;DR

This paper introduces a new positional encoding technique for implicit neural representations that enhances reconstruction quality and rate-distortion performance without added complexity, benefiting compact data representation and novel view synthesis.

Contribution

The paper proposes a novel positional encoding method with more frequency bases, improving INR reconstruction quality and compression performance.

Findings

Significant gain in rate-distortion performance

Higher reconstruction quality in novel view synthesis

No additional complexity introduced

Abstract

Positional encodings are employed to capture the high frequency information of the encoded signals in implicit neural representation (INR). In this paper, we propose a novel positional encoding method which improves the reconstruction quality of the INR. The proposed embedding method is more advantageous for the compact data representation because it has a greater number of frequency basis than the existing methods. Our experiments shows that the proposed method achieves significant gain in the rate-distortion performance without introducing any additional complexity in the compression task and higher reconstruction quality in novel view synthesis.