Research map / Video / Video generation
DRFusion: Drift-Resilient Temporally Consistent Infrared–Visible Video Fusion
Xingyuan Li, HaoYuan Xu, Shulin Li, Xiang Chen, Zhiying Jiang, Jinyuan Liu
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 occlusion-aware temporal loss Ltemp in Stage I (ablation) | DRFusion · NOT-156 | CC: 0.442 -> 0.458 | Improved |
| add trained Condition Adapter (ablation) | DRFusion · NOT-156 | SSIM: 0.544 -> 0.612 | Improved |
| add Latent Refinement (ablation) | DRFusion · NOT-156 | CC: 0.328 -> 0.458 | Improved |
| add Stabilized History Guidance (ablation) | DRFusion · NOT-156 | BiSWE: 5.238 -> 4.816 | Improved |
| add context suppression term H(2) (ablation) | DRFusion · NOT-156 | BiSWE: 4.972 -> 4.816 | Improved |
| use DRFusion instead of frame-wise and optical-flow fusion baselines | infrared-visible video fusion · VTMOT | BiSWE: 7.618 -> 7.418 (best baseline TIMFus) | Improved |
| DRFusion versus baselines on temporal metrics | NOT-156 · NOT-156 | BiSWE: 4.816 vs TemCOCO 4.593 | Mixed |
| use DRFusion fused videos as tracker input | ByteTrack + YOLOv11n · NOT-156 | AUC: 0.240 -> 0.252 (best baseline DDFM) | Improved |
| DRFusion versus Mask-Dif on entropy | HDO · HDO | EN: 6.692 vs 6.725 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- TemCOCO — TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration (ICCV 2025) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Degradation-Robust and Temporally Consistent Infrared–Visible Video Fusion via One-step Diffusion Framework (ECCV 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 0.92)
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking (NeurIPS 2025 · similarity 0.88)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation (NeurIPS 2026 · 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.
