Rectified self-supervised monocular depth estimation loss for nighttime and dynamic scenes

Download PDF
Open Webpage

Xiaofei Qin, Lin Wang, Yongchao Zhu, Fan Mao, Xuedian Zhang, Changxiang He, Qiulei Dong

Published: 2025, Last Modified: 05 Nov 2025Eng. Appl. Artif. Intell. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Two masks are introduced to control the calculation of the photometric loss.•A motion flow network predict the motion of moving objects to rectify the reconstruction.•A decoupled training approach is provided.•Boosting the model performance in nighttime and dynamic scenes.