LISU: Low-light indoor scene understanding with joint learning of reflectance restoration

Ning Zhang,Francesco Nex,Norman Kerle,George Vosselman

ISPRS Journal of Photogrammetry and Remote Sensing（2022）

引用 6|浏览3

暂无评分

摘要

•An end-to-end deep learning framework for semantic segmentation in low-light indoor scenes outperforming the state-of-the-art DeepLab v3+.•A new data set contains both rendered and real normal-light/low-light image pairs for studying UAVs or robots understanding low-light indoor scenes.

查看译文

关键词

Semantic segmentation,Deep learning,Intrinsic image decomposition,Low-light

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要