Bayesian Deep Basis Fitting for Depth Completion with Uncertainty

TL;DR

This paper introduces Bayesian Deep Basis Fitting, a method that enhances depth completion by providing reliable uncertainty estimates and effective performance even with sparse data, advancing the state of depth sensing.

Contribution

It extends Deep Basis Fitting with a Bayesian framework to produce calibrated uncertainty estimates and improve depth completion with limited sparse measurements.

Findings

Produces accurate per-pixel uncertainty estimates

Performs well with few or no sparse depth measurements

Outperforms existing uncertainty estimation techniques

Abstract

In this work we investigate the problem of uncertainty estimation for image-guided depth completion. We extend Deep Basis Fitting (DBF) for depth completion within a Bayesian evidence framework to provide calibrated per-pixel variance. The DBF approach frames the depth completion problem in terms of a network that produces a set of low-dimensional depth bases and a differentiable least squares fitting module that computes the basis weights using the sparse depths. By adopting a Bayesian treatment, our Bayesian Deep Basis Fitting (BDBF) approach is able to 1) predict high-quality uncertainty estimates and 2) enable depth completion with few or no sparse measurements. We conduct controlled experiments to compare BDBF against commonly used techniques for uncertainty estimation under various scenarios. Results show that our method produces better uncertainty estimates with accurate depth prediction.