无需干净图像，3D感知模型融合噪点可见光与近红外数据，在暗光下重建清晰图像。
Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark
- 在3D空间中隐式融合极噪声的RGB与NIR信号
- 在合成与真实数据上均优于现有方法，支持多噪声水平泛化
- 适合无清洁数据标注的低光成像场景，如安防监控
低光成像的鲁棒性仍是挑战。近期研究尝试将噪声可见光（RGB）与近红外（NIR）融合以提升增强效果，但多数方法依赖精心配对的训练数据，且在不同场景下泛化能力有限。本文提出一种新视角：通过引入3D感知神经建模，实现无需干净RGB监督的RGB-NIR低光成像。该模型可在3D空间中隐式融合极端噪声的RGB观测与NIR线索，有效恢复出清晰的RGB图像。所提方法避免了清洁RGB数据采集需求，具备跨不同噪声水平的泛化能力。在合成与真实数据上的大量评估验证了其优越性能。代码已开源：https://github.com/MyNiuuu/3DarkFusion。
原文摘要 · Abstract (English)
Robust low-light imaging remains challenging for the community. Recent studies have explored fusing Near-Infrared (NIR) with noisy RGB to achieve improved enhancement, yet most methods depend on carefully curated training data pairs, with limited robustness under different scenarios. This paper offers a new perspective for RGB-NIR low-light imaging by incorporating 3D-aware neural modeling. Without using clean RGB supervision, a powerful model can be optimized to implicitly fuse extremely noisy RGB observations with NIR cues in 3D space, effectively recovering clean RGB images. The proposed model obviates the requirement for clean RGB data collection, generalizes across different noise levels. Extensive evaluations on synthetic and real data demonstrate its superiority. Codes available: https://github.com/MyNiuuu/3DarkFusion
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。