MINR: Efficient Implicit Neural Representations for Multi-Image Encoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Wenyong, Wu, Taiqiang, Liu, Zhengwu, Cheng, Yuxin, Zhang, Chen, Wong, Ngai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911110990397440
author Zhou, Wenyong
Wu, Taiqiang
Liu, Zhengwu
Cheng, Yuxin
Zhang, Chen
Wong, Ngai
author_facet Zhou, Wenyong
Wu, Taiqiang
Liu, Zhengwu
Cheng, Yuxin
Zhang, Chen
Wong, Ngai
contents Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to computational and storage inefficiencies when encoding multi-images. To address this issue, we propose MINR, sharing specific layers to encode multi-image efficiently. We first compare the layer-wise weight distributions for several trained INRs and find that corresponding intermediate layers follow highly similar distribution patterns. Motivated by this, we share these intermediate layers across multiple images while preserving the input and output layers as input-specific. In addition, we design an extra novel projection layer for each image to capture its unique features. Experimental results on image reconstruction and super-resolution tasks demonstrate that MINR can save up to 60\% parameters while maintaining comparable performance. Particularly, MINR scales effectively to handle 100 images, maintaining an average peak signal-to-noise ratio (PSNR) of 34 dB. Further analysis of various backbones proves the robustness of the proposed MINR.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13471
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MINR: Efficient Implicit Neural Representations for Multi-Image Encoding
Zhou, Wenyong
Wu, Taiqiang
Liu, Zhengwu
Cheng, Yuxin
Zhang, Chen
Wong, Ngai
Computer Vision and Pattern Recognition
Implicit Neural Representations (INRs) aim to parameterize discrete signals through implicit continuous functions. However, formulating each image with a separate neural network~(typically, a Multi-Layer Perceptron (MLP)) leads to computational and storage inefficiencies when encoding multi-images. To address this issue, we propose MINR, sharing specific layers to encode multi-image efficiently. We first compare the layer-wise weight distributions for several trained INRs and find that corresponding intermediate layers follow highly similar distribution patterns. Motivated by this, we share these intermediate layers across multiple images while preserving the input and output layers as input-specific. In addition, we design an extra novel projection layer for each image to capture its unique features. Experimental results on image reconstruction and super-resolution tasks demonstrate that MINR can save up to 60\% parameters while maintaining comparable performance. Particularly, MINR scales effectively to handle 100 images, maintaining an average peak signal-to-noise ratio (PSNR) of 34 dB. Further analysis of various backbones proves the robustness of the proposed MINR.
title MINR: Efficient Implicit Neural Representations for Multi-Image Encoding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.13471