UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sudhakar, Soumya, Karaman, Sertac, Sze, Vivienne
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911707353317376
author Sudhakar, Soumya
Karaman, Sertac
Sze, Vivienne
author_facet Sudhakar, Soumya
Karaman, Sertac
Sze, Vivienne
contents Reliable uncertainty estimation is critical for deploying monocular depth deep neural networks (DNNs) in safety-critical robotic systems. Conventional uncertainty methods such as ensembles and sampling-based approaches require multiple inferences per image, incurring substantial compute and memory overhead. Moreover, uncertainty predicted from a single image misses out on measuring disagreement between predictions across views of the same region. We propose Uncertainty from Motion* (UfM*), an uncertainty estimation algorithm that measures multiview disagreement efficiently by comparing previous and current views using a compact Gaussian mixture, requiring only a single DNN inference per image. Using Gaussians to compute multiview disagreement is not only more compute- and memory-efficient than a prior approach using a point cloud, but also improves uncertainty by measuring disagreement across regions of 3D space. UfM* paired with aleatoric uncertainty improves expected calibration error by 24-28% compared to an ensemble, while requiring only 3% of the energy and 0.02% of the memory on 100 out-of-distribution ScanNet sequences. We demonstrate UfM* consumes only 63 mJ per 224x224 image while running real-time at 30 FPS on an Arm Cortex-A76 CPU onboard a miniature energy-constrained robot, highlighting that measuring multiview disagreement using Gaussians enables efficient uncertainty for resource-constrained robotic systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23098
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians
Sudhakar, Soumya
Karaman, Sertac
Sze, Vivienne
Robotics
Reliable uncertainty estimation is critical for deploying monocular depth deep neural networks (DNNs) in safety-critical robotic systems. Conventional uncertainty methods such as ensembles and sampling-based approaches require multiple inferences per image, incurring substantial compute and memory overhead. Moreover, uncertainty predicted from a single image misses out on measuring disagreement between predictions across views of the same region. We propose Uncertainty from Motion* (UfM*), an uncertainty estimation algorithm that measures multiview disagreement efficiently by comparing previous and current views using a compact Gaussian mixture, requiring only a single DNN inference per image. Using Gaussians to compute multiview disagreement is not only more compute- and memory-efficient than a prior approach using a point cloud, but also improves uncertainty by measuring disagreement across regions of 3D space. UfM* paired with aleatoric uncertainty improves expected calibration error by 24-28% compared to an ensemble, while requiring only 3% of the energy and 0.02% of the memory on 100 out-of-distribution ScanNet sequences. We demonstrate UfM* consumes only 63 mJ per 224x224 image while running real-time at 30 FPS on an Arm Cortex-A76 CPU onboard a miniature energy-constrained robot, highlighting that measuring multiview disagreement using Gaussians enables efficient uncertainty for resource-constrained robotic systems.
title UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians
topic Robotics
url https://arxiv.org/abs/2605.23098