DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion

By Zixiang Zhao, Shuang Xu, Chunxia Zhang, Junmin Liu, Pengfei Li, Jiangshe Zhang. International Joint Conference on Artificial Intelligence, 2020

395 citations recorded by the source corpus.

Infrared and visible image fusion, a hot topic in the field of image processing, aims at obtaining fused images keeping the advantages of source images. This paper proposes a novel auto-encoder (AE) based fusion network. The core idea is that the encoder decomposes an image into background and detail feature maps with low- and high-frequency information, respectively, and that the decoder recovers the original image. To this end, the loss function makes the background/detail feature maps of source images similar/dissimilar. In the test phase, background and detail feature maps are respectively merged via a fusion module, and the fused image is recovered by the decoder. Qualitative and quantitative results illustrate that our method can generate fusion images containing highlighted targets and abundant detail texture information with strong reproducibility and meanwhile surpass state-of-the-art (SOTA) approaches.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/bb8b568310a77b1b7bea20a9443c6dca4278cdc2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Radu Timofte
2. Luc Van Gool
3. Jiayi Ma
4. Yulun Zhang
5. Hui Li
6. Xiao-Jun Wu
7. Linfeng Tang
8. Ming-Hsuan Yang

In Media Technology

1. Radu Timofte
2. Luc Van Gool
3. Yulun Zhang
4. Jiayi Ma
5. Hui Li
6. Linfeng Tang
7. Yiannis Demiris
8. Xingchen Zhang

Citations in the corpus

• CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach (2024, methodology): “Multi-stage fusion methods [20][27][28][29] involve separate processing of the input images before combining them, whereas end-to-end fusion methods [30][24]combine the input images directly.”
• SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, methodology): “In addition, Xu et al. [33], [34] and Zhao et al. [35] promoted the interpretability of AE-based fusion methods via devising multiple encoders to extract specific features.”
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection (2022, background): “Deep learning has achieved promising progress in low-level vision tasks [12, 15, 17, 19, 23, 25, 35, 40] due to the powerful nonlinear fitting ability of multi-layer neural networks.”
• CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (2022, methodology): “The fusion targets include digital [45,84], multi-modal [36,70,88] Figure 1.”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, methodology): “Early efforts [8, 9, 10, 21, 22] tend to achieve excellent fusion effects by adjusting the network structure or loss functions.”
• Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration (2022, methodology): “We perform quantitative and qualitative evaluations for the proposed method against several state-of-the-art IVIF methods, including DENSE [Li and Wu, 2019], DIDFuse [Zhao et al., 2020], FGAN [Ma et al.”