Research map / Image generation / Image restoration
LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images
Hui Li, Tianyang Xu, Xiao‐Jun Wu, Jiwen Lu, Josef Kittler
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 pixel-level loss L_pixel to the multi-level loss (ablation) | LRRNet · TNO | VIFm: 0.66009 -> 0.71399 | Improved |
| add pixel-level loss L_pixel to the multi-level loss (ablation) | LRRNet · TNO | SSIMm: 0.71566 -> 0.70625 | Hurt |
| add deep Gram-matrix loss L_deep (ablation) | LRRNet · TNO | VIFm: 0.68830 -> 0.71399 | Improved |
| add deep Gram-matrix loss L_deep (ablation) | LRRNet · TNO | SD: 82.38744 -> 81.78905 | Hurt |
| set gamma4 to 2000 rather than 1500 (ablation) | LRRNet · TNO | VIFm: 0.69263 -> 0.71399 | Improved |
| use 4 LLRR blocks instead of 2 (ablation) | LRRNet · TNO | VIFm: 0.66020 -> 0.71399 | Improved |
| use 4 LLRR blocks instead of 8 (ablation) | LRRNet · TNO | Nabf: 0.16993 -> 0.14168 | Improved |
| use 4 LLRR blocks instead of 6 (ablation) | LRRNet · TNO | En: 6.82875 -> 6.85836 | Improved |
| use LLRR blocks instead of plain conv layers or dense blocks (ablation) | LRRNet · TNO | visual quality | Improved |
| raise gamma2 from 0.1 to 1.5 (with w_ir=3.0) (ablation) | LRRNet · TNO | SD: 65.70380 -> 81.78905 | Improved |
| raise w_ir from 3.0 to 5.0 (gamma2=0.1) (ablation) | LRRNet · TNO | Nabf: 0.17873 -> 0.23034 | Hurt |
| replace RFN with LRRNet as fusion branch in DFAT tracker | DFAT · VOT2020-RGBT | EAO: 0.3840 -> 0.4143 | Improved |
Closest papers by meaning
- An Efficient Image Fusion Network Exploiting Unifying Language and Mask Guidance (TPAMI 2025 · similarity 0.88)
- CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion (IJCV 2023 · similarity 0.88)
- A Task-Guided, Implicitly-Searched and Meta-Initialized Deep Model for Image Fusion (TPAMI 2024 · similarity 0.87)
- A General Image Fusion Approach Exploiting Gradient Transfer Learning and Fusion Rule Unfolding (TPAMI 2026 · similarity 0.87)
- Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion (CVPR 2026 · similarity 0.87)
- Task-driven Image Fusion with Learnable Fusion Loss (CVPR 2025 · similarity 0.85)
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.
