Research map / Video / Video segmentation and tracking
On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer
Zhenjie Yu, Shuang Li, Yirui Shen, Chi Harold Liu, Shuigen Wang
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 Content-aware Optimization (ablation) | CPTrans · IRVI Traffic | FID: 0.3193 -> 0.2936 | Improved |
| Add Content-aware Temporal Normalization (ablation) | CPTrans · IRVI Traffic | FID: 0.3211 -> 0.2936 | Improved |
| Add Content-aware Optimization (ablation) | CPTrans · IRVI Monitoring | FID: 0.7250 -> 0.7004 | Improved |
| Add Content-aware Temporal Normalization (ablation) | CPTrans · IRVI Monitoring | FID: 0.7131 -> 0.7004 | Improved |
| Add Content-aware Optimization (ablation) | CPTrans · InfraredCity-Adverse Rain | FID: 0.5056 -> 0.4760 | Improved |
| Add Content-aware Temporal Normalization (ablation) | CPTrans · InfraredCity-Adverse Rain | FID: 0.4981 -> 0.4760 | Improved |
| Add Content-aware Optimization (ablation) | CPTrans · InfraredCity-Adverse Snow | FID: 0.5174 -> 0.4952 | Improved |
| Add Content-aware Temporal Normalization (ablation) | CPTrans · InfraredCity-Adverse Snow | FID: 0.4962 -> 0.4952 | Improved |
| Use CPTrans instead of ROMA | Unpaired infrared-to-visible translation · IRVI Traffic | FID: 0.3467 -> 0.2936 | Improved |
| Use CPTrans instead of ROMA | Unpaired infrared-to-visible translation · InfraredCity-Adverse Rain | FID: 0.5577 -> 0.4760 | Improved |
| Use CPTrans instead of ROMA | Unpaired infrared-to-visible translation · InfraredCity-Adverse Snow | FID: 0.5393 -> 0.4952 | Improved |
| Use CPTrans instead of ROMA | Unpaired infrared-to-visible translation · IRVI Traffic | KID: 3.0880 -> 1.9178 | Improved |
Closest papers by meaning
- CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation (NeurIPS 2026 · similarity 0.86)
- IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark (ICCV 2025 · similarity 0.86)
- D3F-IR: Dual-Domain Deterministic Flow Matching for Visible-to-Infrared Translation (ECCV 2026 · similarity 0.86)
- Object-Aware NIR-to-Visible Translation (ECCV 2024 · similarity 0.85)
- SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis (CVPR 2026 · similarity 0.83)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.83)
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.
