Research map / Label-efficient and robust learning / Recognition and long-tail
LaRA-Fusion: Latent-Robust Adaptation via Dual-Loop Constraints for Infrared and Visible Image Fusion
Yaru Su, Chaowei Huang, Huangbiao Xu, Xiao Ke
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 inner loop (geometric reversibility) (ablation) | LaRA-Fusion · MSRS test | SD: 43.18 -> 45.73 | Improved |
| add inner loop (geometric reversibility) (ablation) | LaRA-Fusion · MSRS test | MI: 2.68 -> 2.98 | Improved |
| add outer adversarial alignment loop (ablation) | LaRA-Fusion · MSRS test | VIF: 0.96 -> 1.03 | Improved |
| add Manifold Rectification Block (MRB) (ablation) | LaRA-Fusion · MSRS test | Qabf: 0.61 -> 0.66 | Improved |
| add Hierarchical Attribute Arbitration (HAA) (ablation) | LaRA-Fusion · MSRS test | VIF: 0.93 -> 1.03 | Improved |
| add stochastic alpha interpolation with L_attr (ablation) | LaRA-Fusion · MSRS test | SD: 43.37 -> 45.73 | Improved |
| add stochastic alpha interpolation with L_attr (ablation) | LaRA-Fusion · MSRS test | MI: 2.93 -> 2.98 | No clear effect |
| add HAA (ablation) | LaRA-Fusion · MSRS test | MI: 2.98 -> 2.98 | No clear effect |
Closest papers by meaning
- Domain Adaptation Guided Infrared and Visible Image Fusion (AAAI 2026 · similarity 0.91)
- Universal Representation for Real-World Misaligned Infrared-Visible Image Fusion (TPAMI 2026 · similarity 0.88)
- P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation (ECCV 2026 · similarity 0.88)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.85)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.85)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (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.
