# Resolution Invariant Autoencoder

arXiv: https://arxiv.org/abs/2503.09828 · HTML: https://mlsanity.com/paper/2503.09828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining](https://mlsanity.com/paper/2107.09559/) (2021)
- [Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge](https://mlsanity.com/paper/1904.00682/) (2019)
- [Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models](https://mlsanity.com/paper/2206.03461/) (2022)
- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach](https://mlsanity.com/paper/2310.12004/) (2023)
- [Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly Detection](https://mlsanity.com/paper/2304.07147/) (2023)
- [HyperSpace: Hypernetworks for spacing-adaptive image segmentation](https://mlsanity.com/paper/2407.03681/) (2024)

## Abstract (arXiv)

Deep learning has significantly advanced medical imaging analysis, yet variations in image resolution remain an overlooked challenge. Most methods address this by resampling images, leading to either information loss or computational inefficiencies. While solutions exist for specific tasks, no unified approach has been proposed. We introduce a resolution-invariant autoencoder that adapts spatial resizing at each layer in the network via a learned variable resizing process, replacing fixed spatial down/upsampling at the traditional factor of 2. This ensures a consistent latent space resolution, regardless of input or output resolution. Our model enables various downstream tasks to be performed on an image latent whilst maintaining performance across different resolutions, overcoming the shortfalls of traditional methods. We demonstrate its effectiveness in uncertainty-aware super-resolution, classification, and generative modelling tasks and show how our method outperforms conventional baselines with minimal performance loss across resolutions.