Uncertainty from Motion for DNN Monocular Depth Estimation
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 popu...
Main Authors: | Sze, Vivienne (Author), Karaman, Sertac (Author), Sudhakar, Soumya (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
2022-03-29T12:01:20Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Uncertainty from Motion for DNN Monocular Depth Estimation
by: Sudhakar, Soumya, et al.
Published: (2022) -
FastDepth: Fast monocular depth estimation on embedded systems
by: Wofk, Diana, et al.
Published: (2020) -
Balancing Actuation and Computing Energy in Motion Planning
by: Sudhakar, Soumya, et al.
Published: (2021) -
Balancing Actuation and Computing Energy in Motion Planning
by: Sudhakar, Soumya, et al.
Published: (2021) -
Self-supervised sparse-to-dense: Self-supervised depth completion from LiDAR and monocular camera
by: Ma, Fangchang, et al.
Published: (2020)