Search papers, labs, and topics across Lattice.
The paper introduces Any2Full, a one-stage depth completion framework that leverages a pretrained monocular depth estimation (MDE) model and reformulates depth completion as a scale-prompting adaptation task. A Scale-Aware Prompt Encoder is designed to distill scale cues from sparse depth inputs into unified scale prompts, guiding the MDE model to generate globally scale-consistent predictions. Experiments demonstrate Any2Full's superior robustness and efficiency, outperforming existing methods like OMNI-DC by 32.2% in average AbsREL and achieving a 1.4x speedup over PriorDA.
Forget two-stage depth completion pipelines: Any2Full achieves state-of-the-art results with a single-stage prompting approach that's both faster and more accurate.
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.
