# Fitting Segmentation Networks on Varying Image Resolutions using Splatting

arXiv: https://arxiv.org/abs/2206.06445 · HTML: https://mlsanity.com/paper/2206.06445/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 13 Jun 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge](https://mlsanity.com/paper/1904.00682/) (2019)
- [Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis](https://mlsanity.com/paper/2002.05000/) (2020)
- [HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation](https://mlsanity.com/paper/1804.02967/) (2018)
- [Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation](https://mlsanity.com/paper/1711.01468/) (2017)
- [Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches](https://mlsanity.com/paper/1911.13169/) (2019)

## Built on by (most cited first, 1 of 1)

- [Learning from spatially inhomogenous data: resolution-adaptive convolutions for multiple sclerosis lesion segmentation](https://mlsanity.com/paper/2503.21829/) (2025)

## Abstract (arXiv)

Data used in image segmentation are not always defined on the same grid. This is particularly true for medical images, where the resolution, field-of-view and orientation can differ across channels and subjects. Images and labels are therefore commonly resampled onto the same grid, as a pre-processing step. However, the resampling operation introduces partial volume effects and blurring, thereby changing the effective resolution and reducing the contrast between structures. In this paper we propose a splat layer, which automatically handles resolution mismatches in the input data. This layer pushes each image onto a mean space where the forward pass is performed. As the splat operator is the adjoint to the resampling operator, the mean-space prediction can be pulled back to the native label space, where the loss function is computed. Thus, the need for explicit resolution adjustment using interpolation is removed. We show on two publicly available datasets, with simulated and real multi-modal magnetic resonance images, that this model improves segmentation results compared to resampling as a pre-processing step.