Feb 3
Self-supervised depth estimation even in night images using illumination uncertainty with STEPS
Self-supervised depth estimation even in night images using illumination uncertainty with STEPS
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
arXiv paper abstract https://arxiv.org/abs/2302.01334
arXiv PDF paper https://arxiv.org/pdf/2302.01334.pdf
GitHub https://github.com/ucaszyp/steps
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.
… propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task.
… 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.
… benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
