arXiv Analytics

Sign in

arXiv:2302.01334 [cs.CV]AbstractReferencesReviewsResources

STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation

Yupeng Zheng, Chengliang Zhong, Pengfei Li, Huan-ang Gao, Yuhang Zheng, Bu Jin, Ling Wang, Hao Zhao, Guyue Zhou, Qichao Zhang, Dongbin Zhao

Published 2023-02-02Version 1

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised nighttime image enhancement methods have been proposed, their generalization performance in challenging driving scenarios is not satisfactory. To this end, we propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task. Our method tightly entangles two self-supervised tasks using a newly proposed uncertain pixel masking strategy. This strategy originates from the observation that nighttime images not only suffer from underexposed regions but also from overexposed regions. By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally. We benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them. Detailed ablations also reveal the mechanism of our proposal. Last but not least, to mitigate the problem of sparse ground truth of existing datasets, we provide a new photo-realistically enhanced nighttime dataset based upon CARLA. It brings meaningful new challenges to the community. Codes, data, and models are available at

Related articles: Most relevant | Search more
arXiv:1604.07480 [cs.CV] (Published 2016-04-25)
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
arXiv:2002.10534 [cs.CV] (Published 2020-02-24)
Evaluating Registration Without Ground Truth
arXiv:2003.08933 [cs.CV] (Published 2020-03-19)
Depth Estimation by Learning Triangulation and Densification of Sparse Points for Multi-view Stereo