Research map / Video / Video generation
Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework
Songcheng Du, HaoYuan Xu, Xingyuan Li, Yang Zou, Jinyuan Liu, YUNPENG BAI, Ying Li
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 |
|---|---|---|---|
| use fusion-first instead of temporal-first ordering (ablation) | DRT-VF · NOT-156 | MS2R: 0.652 -> 0.574 | Improved |
| add Stage II temporal modeling (ablation) | DRT-VF · NOT-156 | BiSWE: 9.684 -> 7.542 | Improved |
| add Stage II temporal modeling (single-frame quality) (ablation) | DRT-VF · M3SVD | VIF: 0.941 -> 0.934 | Mixed |
| add MCA module instead of simple concatenation (ablation) | DRT-VF · M3SVD | MI: 3.214 -> 3.373 | Improved |
| add one-step DiT backbone (ablation) | DRT-VF · M3SVD | SSIM: 0.672 -> 0.712 | Improved |
| add GTC module (ablation) | DRT-VF · NOT-156 | BiSWE: 9.458 -> 7.542 | Improved |
| add LMC module (ablation) | DRT-VF · NOT-156 | MS2R: 0.694 -> 0.574 | Improved |
| add DCN alignment in LMC (ablation) | DRT-VF · NOT-156 | MS2R: 0.685 -> 0.574 | Improved |
| add Context Aggregation branch (ablation) | DRT-VF · M3SVD | VIF: 0.912 -> 0.934 | Improved |
| add Boundary Refinement branch (ablation) | DRT-VF · NOT-156 | SSIM: 0.631 -> 0.642 | Improved |
| add Boundary Refinement branch (ablation) | DRT-VF · M3SVD | MS2R: 0.246 -> 0.222 | Improved |
| add Context Aggregation branch (ablation) | DRT-VF · NOT-156 | MI: 4.367 -> 4.449 | Improved |
Closest papers by meaning
- DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion (ICML 2026 · similarity 0.93)
- MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction (ECCV 2026 · similarity 0.92)
- Streaming Diffusion Model for Fast Infrared and Visible Video Fusion (CVPR 2026 · similarity 0.91)
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.90)
- TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration (ICCV 2025 · similarity 0.90)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.86)
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.
