用扩散模型检测深度图不可靠区域并修复，提升精度与可靠性。
Perfecting Depth: Uncertainty-Aware Enhancement of Metric Depth
- 分两阶段：先用扩散模型识别不靠谱区域，再基于不确定性图修复
- 在真实场景下生成无伪影、高密度的深度图，提升可靠性
- 适合自动驾驶、机器人等对深度精度要求高的应用
我们提出一种名为 Perfecting Depth 的新型两阶段传感器深度增强框架。该框架利用扩散模型的随机性，自动检测不可靠的深度区域，同时保留几何结构信息。第一阶段（随机估计）通过训练-推理域差异，识别不可靠测量并推断几何结构；第二阶段（确定性优化）基于第一阶段生成的不确定性图，强化结构一致性与像素级精度。结合随机不确定性建模与确定性精修，方法可生成稠密、无伪影的深度图，显著提升可靠性。实验表明其在多样真实场景中均有效。理论分析、多组实验和可视化进一步验证了其鲁棒性与可扩展性。本框架为传感器深度增强设立了新基准，潜在应用于自动驾驶、机器人及沉浸式技术。
原文摘要 · Abstract (English)
We propose a novel two-stage framework for sensor depth enhancement, called Perfecting Depth. This framework leverages the stochastic nature of diffusion models to automatically detect unreliable depth regions while preserving geometric cues. In the first stage (stochastic estimation), the method identifies unreliable measurements and infers geometric structure by leveraging a training-inference domain gap. In the second stage (deterministic refinement), it enforces structural consistency and pixel-level accuracy using the uncertainty map derived from the first stage. By combining stochastic uncertainty modeling with deterministic refinement, our method yields dense, artifact-free depth maps with improved reliability. Experimental results demonstrate its effectiveness across diverse real-world scenarios. Furthermore, theoretical analysis, various experiments, and qualitative visualizations validate its robustness and scalability. Our framework sets a new baseline for sensor depth enhancement, with potential applications in autonomous driving, robotics, and immersive technologies.
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。