# Bayesian Deep Neural Networks for Supervised Learning of Single-View Depth

arXiv: https://arxiv.org/abs/2104.14202 · HTML: https://mlsanity.com/paper/2104.14202/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020)
- [Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision](https://mlsanity.com/paper/1906.01620/) (2019)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Practical Deep Learning with Bayesian Principles](https://mlsanity.com/paper/1906.02506/) (2019)
- [Evaluating Bayesian Deep Learning Methods for Semantic Segmentation](https://mlsanity.com/paper/1811.12709/) (2018)
- [Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow](https://mlsanity.com/paper/1802.07095/) (2018)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)
- [Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation](https://mlsanity.com/paper/1908.00598/) (2019)
- [To Learn or Not to Learn: Visual Localization from Essential Matrices](https://mlsanity.com/paper/1908.01293/) (2019)
- [Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction](https://mlsanity.com/paper/2004.10681/) (2020)
- [Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning](https://mlsanity.com/paper/1907.00865/) (2019)
- [SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth](https://mlsanity.com/paper/1612.05079/) (2016)
- [Inferring Distributions Over Depth from a Single Image](https://mlsanity.com/paper/1912.06268/) (2019)

## Built on by (most cited first, 3 of 3)

- [LightDepth: Single-View Depth Self-Supervision from Illumination Decline](https://mlsanity.com/paper/2308.10525/) (2023)
- [Bayesian Deep Learning for Affordance Segmentation in images](https://mlsanity.com/paper/2303.00871/) (2023)
- [On the Uncertain Single-View Depths in Colonoscopies](https://mlsanity.com/paper/2112.08906/) (2021)

## Abstract (arXiv)

Uncertainty quantification is essential for robotic perception, as overconfident or point estimators can lead to collisions and damages to the environment and the robot. In this paper, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles. For MC dropout, in particular, we explore the effect of the dropout at different levels in the architecture. We show that adding dropout in all layers of the encoder brings better results than other variations found in the literature. This configuration performs similarly to deep ensembles with a much lower memory footprint, which is relevant forapplications. Finally, we explore the use of depth uncertainty for pseudo-RGBD ICP and demonstrate its potential to estimate accurate two-view relative motion with the real scale.