MMA-UNet: A Multi-Modal Asymmetric UNet Architecture for Infrared and Visible Image Fusion
- URL: http://arxiv.org/abs/2404.17747v2
- Date: Thu, 11 Jul 2024 05:32:21 GMT
- Title: MMA-UNet: A Multi-Modal Asymmetric UNet Architecture for Infrared and Visible Image Fusion
- Authors: Jingxue Huang, Xilai Li, Tianshu Tan, Xiaosong Li, Tao Ye,
- Abstract summary: Multi-modal image fusion (MMIF) maps useful information from various modalities into the same representation space.
The existing fusion algorithms tend to symmetrically fuse the multi-modal images, causing the loss of shallow information or bias towards a single modality.
In this study, we analyzed the spatial distribution differences of information in different modalities and proved that encoding features within the same network is not conducive to achieving simultaneous deep feature space alignment.
- Score: 4.788349093716269
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-modal image fusion (MMIF) maps useful information from various modalities into the same representation space, thereby producing an informative fused image. However, the existing fusion algorithms tend to symmetrically fuse the multi-modal images, causing the loss of shallow information or bias towards a single modality in certain regions of the fusion results. In this study, we analyzed the spatial distribution differences of information in different modalities and proved that encoding features within the same network is not conducive to achieving simultaneous deep feature space alignment for multi-modal images. To overcome this issue, a Multi-Modal Asymmetric UNet (MMA-UNet) was proposed. We separately trained specialized feature encoders for different modal and implemented a cross-scale fusion strategy to maintain the features from different modalities within the same representation space, ensuring a balanced information fusion process. Furthermore, extensive fusion and downstream task experiments were conducted to demonstrate the efficiency of MMA-UNet in fusing infrared and visible image information, producing visually natural and semantically rich fusion results. Its performance surpasses that of the state-of-the-art comparison fusion methods.
Related papers
- Rethinking Normalization Strategies and Convolutional Kernels for Multimodal Image Fusion [25.140475569677758]
Multimodal image fusion aims to integrate information from different modalities to obtain a comprehensive image.
Existing methods tend to prioritize natural image fusion and focus on information complementary and network training strategies.
This paper dissects the significant differences between the two tasks regarding fusion goals, statistical properties, and data distribution.
arXiv Detail & Related papers (2024-11-15T08:36:24Z) - Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond [74.96466744512992]
The essence of image fusion is to integrate complementary information from source images.
DeFusion++ produces versatile fused representations that can enhance the quality of image fusion and the effectiveness of downstream high-level vision tasks.
arXiv Detail & Related papers (2024-10-16T06:28:49Z) - Fusion-Mamba for Cross-modality Object Detection [63.56296480951342]
Cross-modality fusing information from different modalities effectively improves object detection performance.
We design a Fusion-Mamba block (FMB) to map cross-modal features into a hidden state space for interaction.
Our proposed approach outperforms the state-of-the-art methods on $m$AP with 5.9% on $M3FD$ and 4.9% on FLIR-Aligned datasets.
arXiv Detail & Related papers (2024-04-14T05:28:46Z) - From Text to Pixels: A Context-Aware Semantic Synergy Solution for
Infrared and Visible Image Fusion [66.33467192279514]
We introduce a text-guided multi-modality image fusion method that leverages the high-level semantics from textual descriptions to integrate semantics from infrared and visible images.
Our method not only produces visually superior fusion results but also achieves a higher detection mAP over existing methods, achieving state-of-the-art results.
arXiv Detail & Related papers (2023-12-31T08:13:47Z) - A Dual Domain Multi-exposure Image Fusion Network based on the
Spatial-Frequency Integration [57.14745782076976]
Multi-exposure image fusion aims to generate a single high-dynamic image by integrating images with different exposures.
We propose a novelty perspective on multi-exposure image fusion via the Spatial-Frequency Integration Framework, named MEF-SFI.
Our method achieves visual-appealing fusion results against state-of-the-art multi-exposure image fusion approaches.
arXiv Detail & Related papers (2023-12-17T04:45:15Z) - Bridging the Gap between Multi-focus and Multi-modal: A Focused
Integration Framework for Multi-modal Image Fusion [5.417493475406649]
Multi-modal image fusion (MMIF) integrates valuable information from different modality images into a fused one.
This paper proposes a MMIF framework for joint focused integration and modalities information extraction.
The proposed algorithm can surpass the state-of-the-art methods in visual perception and quantitative evaluation.
arXiv Detail & Related papers (2023-11-03T12:58:39Z) - Equivariant Multi-Modality Image Fusion [124.11300001864579]
We propose the Equivariant Multi-Modality imAge fusion paradigm for end-to-end self-supervised learning.
Our approach is rooted in the prior knowledge that natural imaging responses are equivariant to certain transformations.
Experiments confirm that EMMA yields high-quality fusion results for infrared-visible and medical images.
arXiv Detail & Related papers (2023-05-19T05:50:24Z) - Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image
Fusion [59.19469551774703]
Infrared and visible image fusion aims to integrate comprehensive information from multiple sources to achieve superior performances on various practical tasks.
We propose a dynamic image fusion framework with a multi-modal gated mixture of local-to-global experts.
Our model consists of a Mixture of Local Experts (MoLE) and a Mixture of Global Experts (MoGE) guided by a multi-modal gate.
arXiv Detail & Related papers (2023-02-02T20:06:58Z) - Unsupervised Image Fusion Method based on Feature Mutual Mapping [16.64607158983448]
We propose an unsupervised adaptive image fusion method to address the above issues.
We construct a global map to measure the connections of pixels between the input source images.
Our method achieves superior performance in both visual perception and objective evaluation.
arXiv Detail & Related papers (2022-01-25T07:50:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.