# MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy

arXiv: https://arxiv.org/abs/2602.24222 · HTML: https://mlsanity.com/paper/2602.24222/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [MPViT: Multi-Path Vision Transformer for Dense Prediction](https://mlsanity.com/paper/2112.11010/) (2021)
- [Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images](https://mlsanity.com/paper/1905.06368/) (2019)
- [Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensing](https://mlsanity.com/paper/2401.15855/) (2024)
- [ResFormer: Scaling ViTs with Multi-Resolution Training](https://mlsanity.com/paper/2212.00776/) (2022)
- [ViTAR: Vision Transformer with Any Resolution](https://mlsanity.com/paper/2403.18361/) (2024)
- [ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices](https://mlsanity.com/paper/2506.03737/) (2025)
- [HoloHisto: End-to-end Gigapixel WSI Segmentation with 4K Resolution Sequential Tokenization](https://mlsanity.com/paper/2407.03307/) (2024)

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

- [CoordFormer: Give Me Any Coordinates and I Will Give You Labels](https://mlsanity.com/paper/2609.08660/) (2026)

## Abstract (arXiv)

Modern microscopy routinely produces gigapixel images that contain structures across multiple spatial scales, from fine cellular morphology to broader tissue organization. Many analysis tasks require combining these scales, yet most vision models operate at a single resolution or derive multi-scale features from one view, limiting their ability to exploit the inherently multi-resolution nature of microscopy data. We introduce MuViT, a transformer architecture built to fuse true multi-resolution observations from the same underlying image. MuViT embeds all patches into a shared world-coordinate system and extends rotary positional embeddings to these coordinates, enabling attention to integrate wide-field context with high-resolution detail within a single encoder. Across synthetic benchmarks, kidney histopathology, and high-resolution mouse-brain microscopy, MuViT delivers consistent improvements over strong ViT and CNN baselines. Multi-resolution MAE pretraining further produces scale-consistent representations that enhance downstream tasks. These results demonstrate that explicit world-coordinate modelling provides a simple yet powerful mechanism for leveraging multi-resolution information in large-scale microscopy analysis.