Aerial Single-View Depth Completion with Image-Guided Uncertainty Estimation
OPEN ACCESS
Loading...
Author / Producer
Date
2020-01
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
On the pursuit of autonomous flying robots, the scientific community
has been developing onboard real-time algorithms for localisation,
mapping and planning. Despite recent progress, the available solutions
still lack accuracy and robustness in many aspects. While mapping for
autonomous cars had a substantive boost using deep-learning techniques
to enhance LIDAR measurements using image-based depth completion, the
large viewpoint variations experienced by aerial vehicles are still
posing major challenges for learning-based mapping approaches. In this
paper, we propose a depth completion and uncertainty estimation
approach that better handles the challenges of aerial platforms, such
as large viewpoint and depth variations, and limited computing
resources. The core of our method is a novel compact network that
performs both depth completion and confidence estimation using an
image-guided approach. Real-time performance onboard a GPU suitable for
small flying robots is achieved by sharing deep features between both
tasks. Experiments demonstrate that our network outperforms the
state-of-the-art in depth completion and uncertainty estimation for
single-view methods on mobile GPUs. We further present a new
photorealistic aerial depth completion dataset that exhibits more
challenging depth completion scenarios than the established indoor and
car driving datasets. The dataset includes an open-source,
visual-inertial UAV simulator for photo-realistic data generation. Our
results show that our network trained on this dataset can be directly
deployed on real-world outdoor aerial public datasets without
fine-tuning or style transfer.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
5 (2)
Pages / Article No.
1055 - 1062
Publisher
IEEE
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Deep Learning in Robotics and Automation; Perception and autonomy; Aerial robotics
Organisational unit
03766 - Pollefeys, Marc / Pollefeys, Marc
09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former)
Notes
Funding
157585 - Collaborative vision-based perception for teams of (aerial) robots (SNF)