Uncertainty from Motion for DNN Monocular Depth Estimation
Name
2022_icra_ufm.pdf
Size
1.33 MB
Format
Unknown
Checksum (MD5)
d61f686452983fb434e8bb2cc0516617
Author(s)
Sudhakar, Soumya
Sze, Vivienne
Karaman, Sertac
Date Issued
May 23, 2022
Journal
IEEE International Conference on Robotics and Automation (ICRA)
Citation
Sze, Vivienne, Karaman, Sertac and Sudhakar, Soumya. 2022. "Uncertainty from Motion for DNN Monocular Depth Estimation." IEEE International Conference on Robotics and Automation (ICRA).
Version
Author's final manuscript
Abstract
Deployment of deep neural networks (DNNs) for
monocular depth estimation in safety-critical scenarios on
resource-constrained platforms requires well-calibrated and
efficient uncertainty estimates. However, many popular uncertainty estimation techniques, including state-of-the-art ensembles and popular sampling-based methods, require multiple
inferences per input, making them difficult to deploy in latencyconstrained or energy-constrained scenarios. We propose a new
algorithm, called Uncertainty from Motion (UfM), that requires
only one inference per input. UfM exploits the temporal redundancy in video inputs by merging incrementally the per-pixel
depth prediction and per-pixel aleatoric uncertainty prediction
of points that are seen in multiple views in the video sequence.
When UfM is applied to ensembles, we show that UfM can
retain the uncertainty quality of ensembles at a fraction of the
energy by running only a single ensemble member at each frame
and fusing the uncertainty over the sequence of frames. In a set
of representative experiments using FCDenseNet and eight indistribution and out-of-distribution video sequences, UfM offers
comparable uncertainty quality to an ensemble of size 10 while
consuming only 11.3% of the ensemble’s energy and running
6.4× faster on a single Nvidia RTX 2080 Ti GPU, enabling
near ensemble uncertainty quality for resource-constrained,
real-time scenarios.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
