English

MINR: Efficient Implicit Neural Representations for Multi-Image Encoding

Computer Vision and Pattern Recognition 2025-08-20 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2508.13471,
  title  = {MINR: Efficient Implicit Neural Representations for Multi-Image Encoding},
  author = {Wenyong Zhou and Taiqiang Wu and Zhengwu Liu and Yuxin Cheng and Chen Zhang and Ngai Wong},
  journal= {arXiv preprint arXiv:2508.13471},
  year   = {2025}
}

Comments

4 pages, 4 figures