Get absolute depth in monocular self-supervised depth estimation by global scale factor with Dana
Get absolute depth in monocular self-supervised depth estimation by global scale factor with Dana
One scalar is all you need -- absolute depth estimation using monocular self-supervision
arXiv paper abstract https://arxiv.org/abs/2303.07662
arXiv PDF paper (starts on page 3) https://arxiv.org/pdf/2303.07662.pdf
Self-supervised monocular depth estimators can be trained or fine-tuned on new scenes using only images and no ground-truth depth data ... However, these estimators suffer from the inherent ambiguity of the depth scale, significantly limiting their applicability.
... present a method for transferring the depth-scale from existing source datasets collected with ground-truth depths to depth estimators that are trained using self-supervision on a newly collected target dataset consisting of images only
... show that self-supervision based on projective geometry results in predicted depths that are linearly correlated with their ground-truth depths.
... utilize this observed property and model the relationship between the ground-truth and the predicted up-to-scale depths of images from the source domain using a single global scalar.
... scale the predicted up-to-scale depths of images from the target domain using the estimated global scaling factor, performing depth-scale transfer between the two domains.
... achieves competitive accuracy on KITTI ... and higher accuracy on DDAD, when using both real or synthetic source datasets.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments