Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement

TL;DR

This paper introduces a sparsity-adaptive depth refinement framework using a masked spatial propagation network, which effectively handles varying sparse depth points and improves depth completion performance.

Contribution

The paper presents the MSPN model and SDR framework that adapt to different levels of sparsity, addressing a key limitation of previous depth completion methods.

Findings

Achieves state-of-the-art results on SDR tasks.

Effectively handles varying sparse depth points.

Improves depth completion accuracy across scenarios.

Abstract

The main function of depth completion is to compensate for an insufficient and unpredictable number of sparse depth measurements of hardware sensors. However, existing research on depth completion assumes that the sparsity -- the number of points or LiDAR lines -- is fixed for training and testing. Hence, the completion performance drops severely when the number of sparse depths changes significantly. To address this issue, we propose the sparsity-adaptive depth refinement (SDR) framework, which refines monocular depth estimates using sparse depth points. For SDR, we propose the masked spatial propagation network (MSPN) to perform SDR with a varying number of sparse depths effectively by gradually propagating sparse depth information throughout the entire depth map. Experimental results demonstrate that MPSN achieves state-of-the-art performance on both SDR and conventional depth completion scenarios.