# VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data

arXiv: https://arxiv.org/abs/2010.08357 · HTML: https://mlsanity.com/paper/2010.08357/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [HIPA: Hierarchical Patch Transformer for Single Image Super Resolution](https://mlsanity.com/paper/2203.10247/) (2022)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [Single-Stage Broad Multi-Instance Multi-Label Learning (BMIML) with Diverse Inter-Correlations and its application to medical image classification](https://mlsanity.com/paper/2209.02625/) (2022)
- [Oversampling errors in multimodal medical imaging are due to the Gibbs effect](https://mlsanity.com/paper/2103.05964/) (2021)
- [Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks](https://mlsanity.com/paper/2306.02886/) (2023)
- [Super-Resolution Based Patch-Free 3D Image Segmentation with High-Frequency Guidance](https://mlsanity.com/paper/2210.14645/) (2022)
- [A residual dense vision transformer for medical image super-resolution with segmentation-based perceptual loss fine-tuning](https://mlsanity.com/paper/2302.11184/) (2023)
- [Efficient and Accurate Hyperspectral Pansharpening Using 3D VolumeNet and 2.5D Texture Transfer](https://mlsanity.com/paper/2203.03951/) (2022)
- [VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution](https://mlsanity.com/paper/2603.23153/) (2026)

## Abstract (arXiv)

Deep learning-based super-resolution (SR) techniques have generally achieved excellent performance in the computer vision field. Recently, it has been proven that three-dimensional (3D) SR for medical volumetric data delivers better visual results than conventional two-dimensional (2D) processing. However, deepening and widening 3D networks increases training difficulty significantly due to the large number of parameters and small number of training samples. Thus, we propose a 3D convolutional neural network (CNN) for SR of medical volumetric data called ParallelNet using parallel connections. We construct a parallel connection structure based on the group convolution and feature aggregation to build a 3D CNN that is as wide as possible with few parameters. As a result, the model thoroughly learns more feature maps with larger receptive fields. In addition, to further improve accuracy, we present an efficient version of ParallelNet (called VolumeNet), which reduces the number of parameters and deepens ParallelNet using a proposed lightweight building block module called the Queue module. Unlike most lightweight CNNs based on depthwise convolutions, the Queue module is primarily constructed using separable 2D cross-channel convolutions. As a result, the number of network parameters and computational complexity can be reduced significantly while maintaining accuracy due to full channel fusion. Experimental results demonstrate that the proposed VolumeNet significantly reduces the number of model parameters and achieves high precision results compared to state-of-the-art methods.