Propagating Confidences through CNNs for Sparse Data Regression

TL;DR

This paper introduces a novel CNN layer for sparse data that propagates confidence scores, improving depth completion accuracy and efficiency, with applications in autonomous systems.

Contribution

It presents an algebraically-constrained convolution layer with confidence propagation and a joint loss function, achieving superior performance with fewer parameters.

Findings

Outperforms state-of-the-art on KITTI depth benchmark

Requires three times fewer parameters

Produces continuous confidence maps for decision support

Abstract

In most computer vision applications, convolutional neural networks (CNNs) operate on dense image data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open problem with numerous applications in autonomous driving, robotics, and surveillance. To tackle this challenging problem, we introduce an algebraically-constrained convolution layer for CNNs with sparse input and demonstrate its capabilities for the scene depth completion task. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. Furthermore, we propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. Comprehensive experiments are performed on the KITTI depth benchmark and the results clearly demonstrate that the proposed approach achieves superior performance while requiring three times fewer parameters than the state-of-the-art methods. Moreover, our approach produces a continuous pixel-wise confidence map enabling information fusion, state inference, and decision support.