CVLGIVNov 10, 2023

Improved Positional Encoding for Implicit Neural Representation based Compact Data Representation

arXiv:2311.06059v14 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses a domain-specific bottleneck in INR-based compression and synthesis, offering incremental improvements for applications like 3D rendering and data storage.

The paper tackles the problem of capturing high-frequency information in implicit neural representations (INR) for compact data representation by proposing a novel positional encoding method, resulting in significant gains in rate-distortion performance without added complexity and higher reconstruction quality in novel view synthesis.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes