Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network

By Linfeng Tang, Jiteng Yuan, Jiayi Ma. Information Fusion, 2022

1,011 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/a5eaa09625b01ec8cebe1550c2781d7e66436bbb

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. Luc Van Gool
2. Radu Timofte
3. Jiayi Ma
4. Hui Li
5. Kai Zhang
6. Yulun Zhang
7. Xiaojun Wu
8. Josef Kittler

In Media Technology

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

Citations in the corpus

• LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images (2023, background): “These deep learning based fusion approaches can be divided into three categories: (1) Pre-trained deep network based fusion methods [17]; (2) Auto-encoder based fusion [18]; (3) End-to-end learning fusion networks [19]”
• SuperFusion: A Versatile Image Registration and Fusion Network with Semantic Awareness (2022, methodology): “For image fusion, we also select five state-of-the-art methods for comparison, including RFN-Nest [32], SeAFusion [22], UMF-CMGR [30], U2Fusion [43], and TarDAL [25].”
• Visible and Infrared Image Fusion Using Deep Learning (2023, methodology): “[108] proposed SeAFusion that considers scene segmentation in the image fusion process.”
• Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “…Case 1— we removed L g to verify the importance of the gradient term for detail compensation, Case 2—we used the maximum gradient term in [3] to replace L g to compensate for the details and verify the effectiveness of different types of gradient terms for our method, and Case 3—we…”
• DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion (2023, methodology): “Inaddition, following [30, 50], the total variation penalty item r ( x ) = (cid:107)∇ x 22 can be also added to make the fusion image f better preserve the texture information from v , where ∇ denotes the gradient operator.”
• Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, background): “Recently, few studies[13, 14, 15, 16, 17] have attempted to design multi-task learning-based loss functions by cascading the fusion network and high-level tasks.”
• CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (2022, methodology): “Subsequently in training stage II, inspaired by [56], the total loss becomes:”
• SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer (2022, methodology): “A single fused image with better scene representation and visual perception facilitates subsequent practical visual applications, such as object detection, tracking, semantic segmentation, scene understanding, etc. [7]–[9].”