# VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution

arXiv: https://arxiv.org/abs/2603.23153 · HTML: https://mlsanity.com/paper/2603.23153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 59 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT](https://mlsanity.com/paper/2307.01984/) (2023)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network](https://mlsanity.com/paper/1803.01417/) (2018)
- [An Arbitrary Scale Super-Resolution Approach for 3D MR Images via Implicit Neural Representation](https://mlsanity.com/paper/2110.14476/) (2021)
- [Brain MRI Super Resolution Using 3D Deep Densely Connected Neural Networks](https://mlsanity.com/paper/1801.02728/) (2018)
- [CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography](https://mlsanity.com/paper/2105.14711/) (2021)
- [Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations](https://mlsanity.com/paper/2303.15065/) (2023)
- [InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model](https://mlsanity.com/paper/2308.12465/) (2023)
- [Brain MRI super-resolution using 3D generative adversarial networks](https://mlsanity.com/paper/1812.11440/) (2018)
- [MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and Better](https://mlsanity.com/paper/2003.01217/) (2020)
- [RPLHR-CT Dataset and Transformer Baseline for Volumetric Super-Resolution from CT Scans](https://mlsanity.com/paper/2206.06253/) (2022)
- [VolumeNet: A Lightweight Parallel Network for Super-Resolution of Medical Volumetric Data](https://mlsanity.com/paper/2010.08357/) (2020)
- [SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution](https://mlsanity.com/paper/2406.03359/) (2024)
- [Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors](https://mlsanity.com/paper/2008.11921/) (2020)
- [Three-Dimensional, Multimodal Synchrotron Data for Machine Learning Applications](https://mlsanity.com/paper/2409.07322/) (2024)

## Abstract (arXiv)

Recent advances in volumetric super-resolution (SR) have demonstrated strong performance in medical and scientific imaging, with transformer- and CNN-based approaches achieving impressive results even at extreme scaling factors. In this work, we show that much of this performance stems from training on downsampled data rather than real low-resolution scans. This reliance on downsampling is partly driven by the scarcity of paired high- and low-resolution 3D datasets. To address this, we introduce VoDaSuRe, a large-scale volumetric dataset containing paired high- and low-resolution scans. When training models on VoDaSuRe, we reveal a significant discrepancy: SR models trained on downsampled data produce substantially sharper predictions than those trained on real low-resolution scans, which smooth fine structures. Conversely, applying models trained on downsampled data to real scans preserves more structure but is inaccurate. Our findings suggest that current SR methods are overstated - when applied to real data, they do not recover structures lost in low-resolution scans and instead predict a smoothed average. We argue that progress in deep learning-based volumetric SR requires datasets with paired real scans of high complexity, such as VoDaSuRe. Our dataset and code are publicly available through: https://augusthoeg.github.io/VoDaSuRe/