Research map / Image generation / Image restoration
Object-Aware NIR-to-Visible Translation
Yunyi Gao, Lin Gu, Qiankun Liu, Ying Fu
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 image decomposition into luminance and reflectance (ablation) | Object-aware NIR2VIS framework · FANVID NIR1 | PSNR: 24.33 -> 25.57 | Improved |
| add segmentation object prior to reflection estimation (ablation) | Object-aware NIR2VIS framework · FANVID NIR1 | PSNR: 24.71 -> 25.57 | Improved |
| add object prior (ablation) | Object-aware NIR2VIS framework · EPFL | FID: 261.48 -> 113.90 | Improved |
| add decomposition (ablation) | Object-aware NIR2VIS framework · ICVL | PSNR: 26.83 -> 27.47 | Improved |
| use NIR1 band input instead of NIR2 band input | Object-aware NIR2VIS framework · FANVID | PSNR: 23.37 -> 25.57 | Improved |
| use proposed method rather than best baseline Retinexformer | Object-aware NIR2VIS framework · FANVID NIR1 | PSNR: 24.61 -> 25.57 | Improved |
| translate NIR to visible with the proposed method before detection | YOLOv8n on translated images · FANVID detection | Car recognition rate: 0.915 -> 0.949 versus CycleGAN | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Retinexformer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 5 of 5 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
- TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation (CVPR 2026 · similarity 0.87)
- CoVisIT: Cross-modal Prior Guided Diffusion Model for Visible-to-Infrared Image Translation (NeurIPS 2026 · similarity 0.86)
- On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer (CVPR 2023 · similarity 0.85)
- LiT: Unifying LiDAR "Languages" with LiDAR Translator (NeurIPS 2024 · similarity 0.84)
- ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models (CVPR 2024 · similarity 0.84)
- ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images (CVPR 2024 · 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.
