Research map / Vision-language and multimodal / Cross-modal learning
FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration
Congcong Bian, Haolong Ma, Hui Li, Zhongwei Shen, Xiaoqing Luo, Xiaoning Song, Xiao-jun Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FusionRegister post-registration to MMDRFuse | MMDRFuse · MSRS SAM segmentation | IoU: 83.6 -> 86.5 | Improved |
| add FusionRegister post-registration to HCLFuse | HCLFuse · M3FD SAM segmentation | IoU: 66.2 -> 80.4 | Improved |
| add FusionRegister post-registration to S4Fusion | S4Fusion · LLVIP SAM segmentation | IoU: 82.8 -> 85.3 | Improved |
| add FusionRegister to TDFusion | TDFusion · MSRS SAM segmentation | IoU: 85.2 -> 86.7 | Improved |
| add FusionRegister to FreqGAN | FreqGAN · MSRS SAM segmentation | IoU: 80.7 -> 84.1 | Improved |
| add Modality Retainment Block (MRB) (ablation) | FusionRegister · MSRS ablation | IoU: 85.6 -> 86.5 | Improved |
| use bi-directional warping instead of one-directional warping (ablation) | FusionRegister · MSRS ablation | IoU: 85.5 -> 86.5 | Improved |
| use gMLP in MRB instead of deformable transformer (ablation) | FusionRegister · MSRS ablation | IoU: 86.0 -> 86.5 | Improved |
| use gMLP in MRB instead of deformable convolution (ablation) | FusionRegister · MSRS ablation | IoU: 84.8 -> 86.5 | Improved |
| increase network depth from two to three layers (ablation) | FusionRegister · MSRS ablation | IoU: 86.5 -> 86.3 | No clear effect |
| add FusionRegister to S4Fusion on M3FD | S4Fusion · M3FD SAM segmentation | IoU: 72.5 -> 75.7 | Improved |
Closest papers by meaning
- MulFS-CAP: Multimodal Fusion-Supervised Cross-Modality Alignment Perception for Unregistered Infrared-Visible Image Fusion (TPAMI 2025 · similarity 0.91)
- Universal Representation for Real-World Misaligned Infrared-Visible Image Fusion (TPAMI 2026 · similarity 0.89)
- Multi-Modal Image Fusion via Intervention-Stable Feature Learning (CVPR 2026 · similarity 0.86)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.84)
- VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception (NeurIPS 2024 · similarity 0.84)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
