# SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling

arXiv: https://arxiv.org/abs/2607.18990 · HTML: https://mlsanity.com/paper/2607.18990/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks](https://mlsanity.com/paper/1312.6229/) (2013)
- [Interpretable Unsupervised Diversity Denoising and Artefact Removal](https://mlsanity.com/paper/2104.01374/) (2021)
- [MicroSSIM: Improved Structural Similarity for Comparing Microscopy Data](https://mlsanity.com/paper/2408.08747/) (2024)
- [DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images](https://mlsanity.com/paper/2306.12109/) (2023)
- [Pixel super-resolved virtual staining of label-free tissue using diffusion models](https://mlsanity.com/paper/2410.20073/) (2024)
- [How Shift Equivariance Impacts Metric Learning for Instance Segmentation](https://mlsanity.com/paper/2101.05846/) (2021)
- [Conditional Variational Diffusion Models](https://mlsanity.com/paper/2312.02246/) (2023)
- [Perceptual Embedding Consistency for Seamless Reconstruction of Tilewise Style Transfer](https://mlsanity.com/paper/1906.00617/) (2019)
- [Tiling artifacts and trade-offs of feature normalization in the segmentation of large biological images](https://mlsanity.com/paper/2503.19545/) (2025)
- [HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching](https://mlsanity.com/paper/2506.22397/) (2025)
- [Unsupervised Denoising for Signal-Dependent and Row-Correlated Imaging Noise](https://mlsanity.com/paper/2310.07887/) (2023)
- [ResMatching: Noise-Resilient Computational Super-Resolution via Guided Conditional Flow Matching](https://mlsanity.com/paper/2510.26601/) (2025)
- [λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy](https://mlsanity.com/paper/2603.23647/) (2026)

## Abstract (arXiv)

SWITi is a test-time method for reducing artifacts in tiled predictions, particularly for neural networks that learn posterior distributions from which solutions are sampled at inference time. Tiled predictions are unavoidable for large image data, and artifacts arise whenever tiles are smaller than a network's receptive field and when tiles are independent posterior samples. SWITi averages overlapping sliding-window predictions, so discrepancies between neighboring samples are spread across shifted tile positions rather than accumulating at fixed seam coordinates. For posterior models, SWITi uses no more tile samples than an MMSE estimate requires and therefore incurs no additional forward passes. Additionally, we introduce two reference-free metrics, the Fraction of Rejected Tests (FRT) and Artifact Severity (ASV), for detecting and quantifying tiling artifacts from a per-tile permutation test that compares the distribution of pixel gradients across tile seams against the surrounding image content. On pre-trained and published image splitting models across three fluorescence microscopy datasets in 2D and 3D, we show that SWITi substantially attenuates stitching seams while also improving reconstruction fidelity and resolution. Since tiling artifacts in posterior predictions can easily be mistaken for biological structures or for boundaries between biological structures, removing or reducing them using SWITi will improve the downstream processing of large image predictions, which is particularly relevant for biomedical data.