朝向暗光環境下穩健且具3D感知的RGB-NIR成像

Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark

July 31, 2026

作者: Muyao Niu, Mingze Ma, Yifan Zhan, Qingtian Zhu, Zhihang Zhong, Wei Guo, Chang Wen Chen, Yinqiang Zheng

cs.AI

摘要

穩健的低光源成像對研究學界而言仍是一項挑戰。近年來的研究探索將近紅外線（NIR）與帶雜訊的RGB影像融合，以達成更佳的影像增強效果，然而多數方法依賴於精心整理的訓練資料對，在不同場景下的穩健性有限。本文提出一個全新的觀點，藉由引入3D感知神經建模來處理RGB-NIR低光源成像問題。在無需乾淨RGB監督的情況下，一個強大的模型可以被最佳化，在3D空間中隱式地融合極度帶雜訊的RGB觀測與NIR線索，有效還原乾淨的RGB影像。所提出的模型免除了收集乾淨RGB資料的需求，並能泛化至不同的雜訊程度。在合成與真實資料上的廣泛評估證實了其優越性。程式碼已公開於：https://github.com/MyNiuuu/3DarkFusion

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