Towards Lossless Implicit Neural Representation via Bit Plane Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Woo Kyoung, Lee, Byeonghun, Cho, Hyunmin, Im, Sunghoon, Jin, Kyong Hwan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916657722556416
author Han, Woo Kyoung
Lee, Byeonghun
Cho, Hyunmin
Im, Sunghoon
Jin, Kyong Hwan
author_facet Han, Woo Kyoung
Lee, Byeonghun
Cho, Hyunmin
Im, Sunghoon
Jin, Kyong Hwan
contents We quantify the upper bound on the size of the implicit neural representation (INR) model from a digital perspective. The upper bound of the model size increases exponentially as the required bit-precision increases. To this end, we present a bit-plane decomposition method that makes INR predict bit-planes, producing the same effect as reducing the upper bound of the model size. We validate our hypothesis that reducing the upper bound leads to faster convergence with constant model size. Our method achieves lossless representation in 2D image and audio fitting, even for high bit-depth signals, such as 16-bit, which was previously unachievable. We pioneered the presence of bit bias, which INR prioritizes as the most significant bit (MSB). We expand the application of the INR task to bit depth expansion, lossless image compression, and extreme network quantization. Our source code is available at https://github.com/WooKyoungHan/LosslessINR
format Preprint
id arxiv_https___arxiv_org_abs_2502_21001
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
Han, Woo Kyoung
Lee, Byeonghun
Cho, Hyunmin
Im, Sunghoon
Jin, Kyong Hwan
Computer Vision and Pattern Recognition
We quantify the upper bound on the size of the implicit neural representation (INR) model from a digital perspective. The upper bound of the model size increases exponentially as the required bit-precision increases. To this end, we present a bit-plane decomposition method that makes INR predict bit-planes, producing the same effect as reducing the upper bound of the model size. We validate our hypothesis that reducing the upper bound leads to faster convergence with constant model size. Our method achieves lossless representation in 2D image and audio fitting, even for high bit-depth signals, such as 16-bit, which was previously unachievable. We pioneered the presence of bit bias, which INR prioritizes as the most significant bit (MSB). We expand the application of the INR task to bit depth expansion, lossless image compression, and extreme network quantization. Our source code is available at https://github.com/WooKyoungHan/LosslessINR
title Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.21001