Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End

06/05/2020
by   Abdelrahman Eldesokey, et al.
48

The focus in deep learning research has been mostly to push the limits of prediction accuracy. However, this was often achieved at the cost of increased complexity, raising concerns about the interpretability and the reliability of deep networks. Recently, an increasing attention has been given to untangling the complexity of deep networks and quantifying their uncertainty for different computer vision tasks. Differently, the task of depth completion has not received enough attention despite the inherent noisy nature of depth sensors. In this work, we thus focus on modeling the uncertainty of depth data in depth completion starting from the sparse noisy input all the way to the final prediction. We propose a novel approach to identify disturbed measurements in the input by learning an input confidence estimator in a self-supervised manner based on the normalized convolutional neural networks (NCNNs). Further, we propose a probabilistic version of NCNNs that produces a statistically meaningful uncertainty measure for the final prediction. When we evaluate our approach on the KITTI dataset for depth completion, we outperform all the existing Bayesian Deep Learning approaches in terms of prediction accuracy, quality of the uncertainty measure, and the computational efficiency. Moreover, our small network with 670k parameters performs on-par with conventional approaches with millions of parameters. These results give strong evidence that separating the network into parallel uncertainty and prediction streams leads to state-of-the-art performance with accurate uncertainty estimates.

READ FULL TEXT

page 1

page 8

page 13

page 15

page 16

page 17

page 18

research
03/29/2021

Bayesian Deep Basis Fitting for Depth Completion with Uncertainty

In this work we investigate the problem of uncertainty estimation for im...
research
04/16/2021

Uncertainty Surrogates for Deep Learning

In this paper we introduce a novel way of estimating prediction uncertai...
research
06/17/2021

Deep Learning Through the Lens of Example Difficulty

Existing work on understanding deep learning often employs measures that...
research
12/21/2019

Depth Completion via Deep Basis Fitting

In this paper we consider the task of image-guided depth completion wher...
research
12/15/2021

Robust Depth Completion with Uncertainty-Driven Loss Functions

Recovering a dense depth image from sparse LiDAR scans is a challenging ...
research
03/11/2021

Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction

Physical motion models offer interpretable predictions for the motion of...
research
12/01/2017

Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection

Motivated by the problem of computer-aided detection (CAD) of pulmonary ...

Please sign up or login with your details

Forgot password? Click here to reset