Any to Full: Prompting Depth Anything for Depth Completion in One Stage

TL;DR

This paper introduces Any2Full, a one-stage, domain-general depth completion framework that reformulates the task as a scale-prompting adaptation of a pretrained monocular depth estimation model, improving robustness and efficiency.

Contribution

It proposes a novel one-stage depth completion method using scale-aware prompts to adapt pretrained MDE models, enhancing generalization and computational efficiency.

Findings

Outperforms OMNI-DC by 32.2% in average AbsREL.

Achieves 1.4× speedup over PriorDA with the same backbone.

Demonstrates superior robustness and efficiency in experiments.

Abstract

Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-fused depth completion methods learn priors jointly conditioned on training RGB distribution and specific depth patterns, limiting domain generalization and robustness to various depth patterns. Recent efforts leverage monocular depth estimation (MDE) models to introduce domain-general geometric priors, but current two-stage integration strategies relying on explicit relative-to-metric alignment incur additional computation and introduce structured distortions. To this end, we present Any2Full, a one-stage, domain-general, and pattern-agnostic framework that reformulates completion as a scale-prompting adaptation of a pretrained MDE model. To address varying depth sparsity levels and irregular spatial distributions, we design a Scale-Aware Prompt Encoder. It distills scale cues from sparse inputs into unified scale prompts, guiding the MDE model toward globally scale-consistent predictions while preserving its geometric priors. Extensive experiments demonstrate that Any2Full achieves superior robustness and efficiency. It outperforms OMNI-DC by 32.2\% in average AbsREL and delivers a 1.4$\times$ speedup over PriorDA with the same MDE backbone, establishing a new paradigm for universal depth completion. Codes and checkpoints are available at https://github.com/zhiyuandaily/Any2Full.