[IPOL announce] new article: Monocular Depth Estimation: a Review of the 2022 State of the Art
announcements about the IPOL journal
announce at list.ipol.im
Fri Jan 27 00:28:10 CET 2023
A new article is available in IPOL: https://www.ipol.im/pub/art/2023/459/
Thibaud Ehret,
Monocular Depth Estimation: a Review of the 2022 State of the Art,
Image Processing On Line, 13 (2023), pp. 38–56.
https://doi.org/10.5201/ipol.2023.459
Abstract
We compare five monocular depth estimation methods based on deep
learning. This comparison focuses on how well methods generalize rather
than a quantitative comparison on a specific dataset. This study shows
that while monocular depth estimation methods work well on images
similar to training images, they often show artifacts when applied on
images out of the training distribution. We evaluate the different
methods with images similar to training data and images with unusual
point of views (e.g. top-down) or paintings. The readers are invited to
judge by themselves about the advantages and drawbacks of all methods by
submitting their own images to the online demo associated with the
present paper.
More information about the announce
mailing list