用稀疏深度数据校准单目模型的相对深度，实现少样本下的精准深度补全。
OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth
- 利用稀疏测量值校准单目模型输出的相对深度，生成伪度量深度先验。
- 仅需少量标注样本即可实现高精度度量深度预测，保持边缘清晰、尺度稳定。
- 适合标签稀缺的现实场景，如自动驾驶和机器人部署。
近期单目基础模型在零样本深度估计上表现优异，但其输出为相对深度而非度量深度，限制了在机器人与自动驾驶中的直接应用。我们发现相对深度能保留全局布局与边界信息：通过稀疏距离测量进行校准，可将其转化为伪度量深度先验。基于此先验，设计了一种精修网络，遵循可靠区域的先验并偏离不可靠区域，从而仅需极少标注样本即可实现准确度量预测。该系统在缺乏精选验证数据时仍能保持稳定的尺度与锐利边缘，在少样本条件下表现突出。结果表明，将基础模型先验与稀疏锚点结合，是应对真实世界标签稀缺问题的可行路径。
原文摘要 · Abstract (English)
Recent monocular foundation models excel at zero-shot depth estimation, yet their outputs are inherently relative rather than metric, limiting direct use in robotics and autonomous driving. We leverage the fact that relative depth preserves global layout and boundaries: by calibrating it with sparse range measurements, we transform it into a pseudo metric depth prior. Building on this prior, we design a refinement network that follows the prior where reliable and deviates where necessary, enabling accurate metric predictions from very few labeled samples. The resulting system is particularly effective when curated validation data are unavailable, sustaining stable scale and sharp edges across few-shot regimes. These findings suggest that coupling foundation priors with sparse anchors is a practical route to robust, deployment-ready depth completion under real-world label scarcity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。