# Towards Generalized Multimodal Homography Estimation

arXiv: https://arxiv.org/abs/2603.03956 · HTML: https://mlsanity.com/paper/2603.03956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [Deep Image Homography Estimation](https://mlsanity.com/paper/1606.03798/) (2016)
- [Equivariant Multi-Modality Image Fusion](https://mlsanity.com/paper/2305.11443/) (2023)
- [Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration](https://mlsanity.com/paper/2205.11876/) (2022)
- [Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model](https://mlsanity.com/paper/1709.03966/) (2017)
- [Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation](https://mlsanity.com/paper/2003.08073/) (2020)
- [Content-Aware Unsupervised Deep Homography Estimation](https://mlsanity.com/paper/1909.05983/) (2019)
- [Deep Homography Estimation for Dynamic Scenes](https://mlsanity.com/paper/2004.02132/) (2020)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [Iterative Deep Homography Estimation](https://mlsanity.com/paper/2203.15982/) (2022)
- [Deep Lucas-Kanade Homography for Multimodal Image Alignment](https://mlsanity.com/paper/2104.11693/) (2021)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection](https://mlsanity.com/paper/2103.15346/) (2021)
- [Perceptual Loss for Robust Unsupervised Homography Estimation](https://mlsanity.com/paper/2104.10011/) (2021)
- [Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging](https://mlsanity.com/paper/2407.02356/) (2024)
- [Object-level Geometric Structure Preserving for Natural Image Stitching](https://mlsanity.com/paper/2402.12677/) (2024)
- [Learning Continuous Depth Representation via Geometric Spatial Aggregator](https://mlsanity.com/paper/2212.03499/) (2022)
- [SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning](https://mlsanity.com/paper/2407.08148/) (2024)
- [Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement](https://mlsanity.com/paper/2507.07230/) (2025)
- [Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization](https://mlsanity.com/paper/2411.13036/) (2024)
- [SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization](https://mlsanity.com/paper/2409.17993/) (2024)
- [Dense Cross-Scale Image Alignment With Fully Spatial Correlation and Just Noticeable Difference Guidance](https://mlsanity.com/paper/2511.09028/) (2025)

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

- [VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation](https://mlsanity.com/paper/2605.17433/) (2026)

## Abstract (arXiv)

Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address this issue, we propose a training data synthesis method that generates unaligned image pairs with ground-truth offsets from a single input image. Our approach renders the image pairs with diverse textures and colors while preserving their structural information. These synthetic data empower the trained model to achieve greater robustness and improved generalization across various domains. Additionally, we design a network to fully leverage cross-scale information and decouple color information from feature representations, thus improving estimation accuracy. Extensive experiments show that our training data synthesis method improves generalization performance. The results also confirm the effectiveness of the proposed network.