# Bi-directional Self-Registration for Misaligned Infrared-Visible Image Fusion

arXiv: https://arxiv.org/abs/2505.06920 · HTML: https://mlsanity.com/paper/2505.06920/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 11 May 2025.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion](https://mlsanity.com/paper/2211.14461/) (2022)
- [Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning](https://mlsanity.com/paper/2003.02437/) (2020)
- [Scalars are universal: Equivariant machine learning, structured like classical physics](https://mlsanity.com/paper/2106.06610/) (2021)
- [RFN-Nest: An end-to-end residual fusion network for infrared and visible images](https://mlsanity.com/paper/2103.04286/) (2021)
- [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)
- [DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2003.09210/) (2020)
- [Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation](https://mlsanity.com/paper/2003.08073/) (2020)
- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://mlsanity.com/paper/2203.14453/) (2022)
- [Imaging with Equivariant Deep Learning](https://mlsanity.com/paper/2209.01725/) (2022)
- [DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior](https://mlsanity.com/paper/2303.06834/) (2023)
- [Improving Misaligned Multi-modality Image Fusion with One-stage Progressive Dense Registration](https://mlsanity.com/paper/2308.11165/) (2023)
- [Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network](https://mlsanity.com/paper/2108.05603/) (2021)
- [Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation](https://mlsanity.com/paper/2204.13656/) (2022)
- [VIFNet: An End-to-end Visible-Infrared Fusion Network for Image Dehazing](https://mlsanity.com/paper/2404.07790/) (2024)
- [FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion](https://mlsanity.com/paper/2209.11277/) (2022)

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

- [SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion](https://mlsanity.com/paper/2609.30703/) (2026)

## Abstract (arXiv)

Acquiring accurately aligned multi-modal image pairs is fundamental for achieving high-quality multi-modal image fusion. To address the lack of ground truth in current multi-modal image registration and fusion methods, we propose a novel self-supervised Bi-directional Self-Registration framework (B-SR). Specifically, B-SR utilizes a proxy data generator (PDG) and an inverse proxy data generator (IPDG) to achieve self-supervised global-local registration. Visible-infrared image pairs with spatially misaligned differences are aligned to obtain global differences through the registration module. The same image pairs are processed by PDG, such as cropping, flipping, stitching, etc., and then aligned to obtain local differences. IPDG converts the obtained local differences into pseudo-global differences, which are used to perform global-local difference consistency with the global differences. Furthermore, aiming at eliminating the effect of modal gaps on the registration module, we design a neighborhood dynamic alignment loss to achieve cross-modal image edge alignment. Extensive experiments on misaligned multi-modal images demonstrate the effectiveness of the proposed method in multi-modal image alignment and fusion against the competing methods. Our code will be publicly available.