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

2026-03-05

AI Summary

This work proposes Any2Full, a single-stage, domain-agnostic, and sparsity-agnostic depth completion framework that addresses the poor generalization and computational inefficiency of existing methods under varying sparsity patterns and domain shifts. By reformulating depth completion as a scale-prompt adaptation problem for pretrained monocular depth estimation (MDE) models, Any2Complete circumvents the distortions and overhead inherent in conventional two-stage approaches. A novel scale-aware prompt encoder enables the model to uniformly handle inputs of arbitrary sparsity and produce end-to-end full-depth predictions. Experiments demonstrate that Any2Full outperforms OMNI-DC by 32.2% in average AbsREL and achieves 1.4× faster inference than PriorDA, significantly enhancing both robustness and efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• depth completion
• domain generalization
• monocular depth estimation
• sparse depth
• scale consistency

Innovation

• depth completion
• monocular depth estimation
• scale prompting
• domain generalization
• one-stage framework