# ZeroReg3D: A Zero-shot Registration Pipeline for 3D Consecutive Histopathology Image Reconstruction

arXiv: https://arxiv.org/abs/2506.21923 · HTML: https://mlsanity.com/paper/2506.21923/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation](https://mlsanity.com/paper/2402.19286/) (2024)
- [ASIGN: An Anatomy-aware Spatial Imputation Graphic Network for 3D Spatial Transcriptomics](https://mlsanity.com/paper/2412.03026/) (2024)
- [Comparison of Consecutive and Re-stained Sections for Image Registration in Histopathology](https://mlsanity.com/paper/2106.13150/) (2021)
- [HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis](https://mlsanity.com/paper/2407.00596/) (2024)
- [MagNet: Multi-Level Attention Graph Network for Predicting High-Resolution Spatial Transcriptomics](https://mlsanity.com/paper/2502.21011/) (2025)
- [DeeperHistReg: Robust Whole Slide Images Registration Framework](https://mlsanity.com/paper/2404.14434/) (2024)
- [Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide Images](https://mlsanity.com/paper/2006.06038/) (2020)
- [Evaluating Cell AI Foundation Models in Kidney Pathology with Human-in-the-Loop Enrichment](https://mlsanity.com/paper/2411.00078/) (2024)
- [Deep Learning-Based Open Source Toolkit for Eosinophil Detection in Pediatric Eosinophilic Esophagitis](https://mlsanity.com/paper/2308.06333/) (2023)
- [Circle Representation for Medical Instance Object Segmentation](https://mlsanity.com/paper/2403.11507/) (2024)
- [Weighted Circle Fusion: Ensembling Circle Representation from Different Object Detection Results](https://mlsanity.com/paper/2406.19540/) (2024)

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

- [Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learning](https://mlsanity.com/paper/2508.14393/) (2025)

## Abstract (arXiv)

Histological analysis plays a crucial role in understanding tissue structure and pathology. While recent advancements in registration methods have improved 2D histological analysis, they often struggle to preserve critical 3D spatial relationships, limiting their utility in both clinical and research applications. Specifically, constructing accurate 3D models from 2D slices remains challenging due to tissue deformation, sectioning artifacts, variability in imaging techniques, and inconsistent illumination. Deep learning-based registration methods have demonstrated improved performance but suffer from limited generalizability and require large-scale training data. In contrast, non-deep-learning approaches offer better generalizability but often compromise on accuracy. In this study, we introduced ZeroReg3D, a novel zero-shot registration pipeline tailored for accurate 3D reconstruction from serial histological sections. By combining zero-shot deep learning-based keypoint matching with optimization-based affine and non-rigid registration techniques, ZeroReg3D effectively addresses critical challenges such as tissue deformation, sectioning artifacts, staining variability, and inconsistent illumination without requiring retraining or fine-tuning. The code has been made publicly available at https://github.com/hrlblab/ZeroReg3D