Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhicheng, Zhu, Hao, Chen, Linsen, Shen, Qiu, Cao, Xun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908650438656000
author Cai, Zhicheng
Zhu, Hao
Chen, Linsen
Shen, Qiu
Cao, Xun
author_facet Cai, Zhicheng
Zhu, Hao
Chen, Linsen
Shen, Qiu
Cao, Xun
contents Implicit neural representation (INR) models signals as continuous functions using neural networks, offering efficient and differentiable optimization for inverse problems across diverse disciplines. However, the representational capacity of INR defined by the range of functions the neural network can characterize, is inherently limited by the low-dimensional feature space in conventional multilayer perceptron (MLP) architectures. While widening the MLP can linearly increase feature space dimensionality, it also leads to a quadratic growth in computational and memory costs. To address this limitation, we propose the split-layer, a novel reformulation of MLP construction. The split-layer divides each layer into multiple parallel branches and integrates their outputs via Hadamard product, effectively constructing a high-degree polynomial space. This approach significantly enhances INR's representational capacity by expanding the feature space dimensionality without incurring prohibitive computational overhead. Extensive experiments demonstrate that the split-layer substantially improves INR performance, surpassing existing methods across multiple tasks, including 2D image fitting, 2D CT reconstruction, 3D shape representation, and 5D novel view synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10142
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature Space
Cai, Zhicheng
Zhu, Hao
Chen, Linsen
Shen, Qiu
Cao, Xun
Computer Vision and Pattern Recognition
Implicit neural representation (INR) models signals as continuous functions using neural networks, offering efficient and differentiable optimization for inverse problems across diverse disciplines. However, the representational capacity of INR defined by the range of functions the neural network can characterize, is inherently limited by the low-dimensional feature space in conventional multilayer perceptron (MLP) architectures. While widening the MLP can linearly increase feature space dimensionality, it also leads to a quadratic growth in computational and memory costs. To address this limitation, we propose the split-layer, a novel reformulation of MLP construction. The split-layer divides each layer into multiple parallel branches and integrates their outputs via Hadamard product, effectively constructing a high-degree polynomial space. This approach significantly enhances INR's representational capacity by expanding the feature space dimensionality without incurring prohibitive computational overhead. Extensive experiments demonstrate that the split-layer substantially improves INR performance, surpassing existing methods across multiple tasks, including 2D image fitting, 2D CT reconstruction, 3D shape representation, and 5D novel view synthesis.
title Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.10142