Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation
Monocular Depth Estimation (MDE) is a fundamental problem in computer vision with numerous applications. Recently, LIDAR-supervised methods have achieved remarkable per-pixel depth accuracy in outdoor scenes. However, significant errors are typically found in the proximity of depth discontinuities,...
Saved in:
Main Authors | , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
10.12.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Monocular Depth Estimation (MDE) is a fundamental problem in computer vision
with numerous applications. Recently, LIDAR-supervised methods have achieved
remarkable per-pixel depth accuracy in outdoor scenes. However, significant
errors are typically found in the proximity of depth discontinuities, i.e.,
depth edges, which often hinder the performance of depth-dependent applications
that are sensitive to such inaccuracies, e.g., novel view synthesis and
augmented reality. Since direct supervision for the location of depth edges is
typically unavailable in sparse LIDAR-based scenes, encouraging the MDE model
to produce correct depth edges is not straightforward. To the best of our
knowledge this paper is the first attempt to address the depth edges issue for
LIDAR-supervised scenes. In this work we propose to learn to detect the
location of depth edges from densely-supervised synthetic data, and use it to
generate supervision for the depth edges in the MDE training. To quantitatively
evaluate our approach, and due to the lack of depth edges GT in LIDAR-based
scenes, we manually annotated subsets of the KITTI and the DDAD datasets with
depth edges ground truth. We demonstrate significant gains in the accuracy of
the depth edges with comparable per-pixel depth accuracy on several challenging
datasets. Code and datasets are available at
\url{https://github.com/liortalker/MindTheEdge}. |
---|---|
DOI: | 10.48550/arxiv.2212.05315 |