无需训练，通过测试时对齐实现跨域深度补全
Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior
- 用预训练的仿射不变深度扩散模型作先验知识
- 测试时优化对齐稀疏度量数据，提升细节清晰度
- 零样本跨域通用，性能比旧方法高21%
深度补全旨在从稀疏深度测量中预测稠密深度图，这是一个病态问题，需依赖先验知识。现有学习方法隐式捕捉先验，但主要适配域内数据，泛化能力差。为此，我们提出一种零样本深度补全方法，包含仿射不变深度扩散模型与测试时对齐机制。利用预训练深度扩散模型作为深度先验，隐式理解场景补全方式。在测试时，将仿射不变深度先验与度量尺度下的稀疏测量对齐，通过优化循环强制其为硬约束。该方法在多个域数据集上展现良好泛化性，平均性能较先前最优方法提升高达21%，同时增强空间理解，锐化场景细节。结果表明，将单目仿射不变深度先验与稀疏度量测量对齐，是实现无需大量训练数据的域泛化深度补全的有效策略。
原文摘要 · Abstract (English)
Depth completion, predicting dense depth maps from sparse depth measurements, is an ill-posed problem requiring prior knowledge. Recent methods adopt learning-based approaches to implicitly capture priors, but the priors primarily fit in-domain data and do not generalize well to out-of-domain scenarios. To address this, we propose a zero-shot depth completion method composed of an affine-invariant depth diffusion model and test-time alignment. We use pre-trained depth diffusion models as depth prior knowledge, which implicitly understand how to fill in depth for scenes. Our approach aligns the affine-invariant depth prior with metric-scale sparse measurements, enforcing them as hard constraints via an optimization loop at test-time. Our zero-shot depth completion method demonstrates generalization across various domain datasets, achieving up to a 21\% average performance improvement over the previous state-of-the-art methods while enhancing spatial understanding by sharpening scene details. We demonstrate that aligning a monocular affine-invariant depth prior with sparse metric measurements is a proven strategy to achieve domain-generalizable depth completion without relying on extensive training data. Project page: https://hyoseok1223.github.io/zero-shot-depth-completion/.
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。