Masked Depth Modeling for Spatial Perception

TL;DR

This paper introduces LingBot-Depth, a depth completion model that uses masked depth modeling and visual context to improve spatial perception, outperforming top RGB-D cameras in depth accuracy and coverage.

Contribution

The paper proposes a novel masked depth modeling approach combined with automated data curation for scalable training of depth completion models.

Findings

Outperforms top-tier RGB-D cameras in depth precision

Provides an aligned latent representation across RGB and depth modalities

Offers a large dataset of 3M RGB-depth pairs for community use

Abstract

Spatial visual perception is a fundamental requirement in physical-world applications like autonomous driving and robotic manipulation, driven by the need to interact with 3D environments. Capturing pixel-aligned metric depth using RGB-D cameras would be the most viable way, yet it usually faces obstacles posed by hardware limitations and challenging imaging conditions, especially in the presence of specular or texture-less surfaces. In this work, we argue that the inaccuracies from depth sensors can be viewed as "masked" signals that inherently reflect underlying geometric ambiguities. Building on this motivation, we present LingBot-Depth, a depth completion model which leverages visual context to refine depth maps through masked depth modeling and incorporates an automated data curation pipeline for scalable training. It is encouraging to see that our model outperforms top-tier RGB-D cameras in terms of both depth precision and pixel coverage. Experimental results on a range of downstream tasks further suggest that LingBot-Depth offers an aligned latent representation across RGB and depth modalities. We release the code, checkpoint, and 3M RGB-depth pairs (including 2M real data and 1M simulated data) to the community of spatial perception.