# Learning Domain-Invariant Representations for Cross-Domain Image Registration via Scene-Appearance Disentanglement

arXiv: https://arxiv.org/abs/2601.08875 · HTML: https://mlsanity.com/paper/2601.08875/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 62 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning](https://mlsanity.com/paper/1805.08651/) (2018)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [SynthMorph: learning contrast-invariant registration without acquired images](https://mlsanity.com/paper/2004.10282/) (2020)
- [Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning](https://mlsanity.com/paper/2112.04489/) (2021)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing](https://mlsanity.com/paper/2408.11823/) (2024)
- [RegWSI: Whole Slide Image Registration using Combined Deep Feature- and Intensity-Based Methods: Winner of the ACROBAT 2023 Challenge](https://mlsanity.com/paper/2404.13108/) (2024)
- [Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method](https://mlsanity.com/paper/2306.16950/) (2023)
- [Zoom and Shift are All You Need](https://mlsanity.com/paper/2406.08866/) (2024)
- [MSMF: Multi-Scale Multi-Modal Fusion for Enhanced Stock Market Prediction](https://mlsanity.com/paper/2409.07855/) (2024)
- [GAF-FusionNet: Multimodal ECG Analysis via Gramian Angular Fields and Split Attention](https://mlsanity.com/paper/2501.01960/) (2024)
- [STEAM-EEG: Spatiotemporal EEG Analysis with Markov Transfer Fields and Attentive CNNs](https://mlsanity.com/paper/2501.01959/) (2024)

## Built on by (most cited first, 3 of 3)

- [SAS-Net: Cross-Domain Image Registration as Inverse Rendering via Structure-Appearance Factorization](https://mlsanity.com/paper/2602.09050/) (2026)
- [PCReg-Net: Progressive Contrast-Guided Registration for Cross-Domain Image Alignment](https://mlsanity.com/paper/2602.13304/) (2026)
- [Deformation-Free Cross-Domain Image Registration via Position-Encoded Temporal Attention](https://mlsanity.com/paper/2602.15959/) (2026)

## Abstract (arXiv)

Image registration under domain shift remains a fundamental challenge in computer vision and medical imaging: when source and target images exhibit systematic intensity differences, the brightness constancy assumption underlying conventional registration methods is violated, rendering correspondence estimation ill-posed. We propose SAR-Net, a unified framework that addresses this challenge through principled scene-appearance disentanglement. Our key insight is that observed images can be decomposed into domain-invariant scene representations and domain-specific appearance codes, enabling registration via re-rendering rather than direct intensity matching. We establish theoretical conditions under which this decomposition enables consistent cross-domain alignment (Proposition 1) and prove that our scene consistency loss provides a sufficient condition for geometric correspondence in the shared latent space (Proposition 2). Empirically, we validate SAR-Net on the ANHIR (Automatic Non-rigid Histological Image Registration) challenge benchmark, where multi-stain histopathology images exhibit coupled domain shift from different staining protocols and geometric distortion from tissue preparation. Our method achieves a median relative Target Registration Error (rTRE) of 0.25%, outperforming the state-of-the-art MEVIS method (0.27% rTRE) by 7.4%, with robustness of 99.1%. Code is available at https://github.com/D-ST-Sword/SAR-NET .