让单目深度估计在各种恶劣环境下都能准，无需标注数据
Depth Anything at Any Condition
- 用无监督一致性正则化，在少量无标签数据上微调模型
- 引入空间距离约束，提升局部细节和语义边界精度
- 零样本适配真实恶劣天气与合成损坏场景，适合实际部署
我们提出 Depth Anything at Any Condition（DepthAnything-AC），一种能够应对多种环境条件的基础单目深度估计（MDE）模型。以往基础 MDE 模型在通用场景表现良好，但在光照变化、恶劣天气和传感器畸变等复杂开放世界环境中性能下降。针对数据稀缺及从受损图像生成高质量伪标签的难题，我们提出一种仅需少量无标签数据的无监督一致性正则化微调范式。此外，我们设计了空间距离约束，显式引导模型学习块级相对关系，从而获得更清晰的语义边界和更精确的细节。实验表明，DepthAnything-AC 在多样基准上具备零样本能力，涵盖真实世界恶劣天气、合成噪声以及通用基准。项目页：https://ghost233lism.github.io/depthanything-AC-page 代码：https://github.com/HVision-NKU/DepthAnythingAC
原文摘要 · Abstract (English)
We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous foundation MDE models achieve impressive performance across general scenes but not perform well in complex open-world environments that involve challenging conditions, such as illumination variations, adverse weather, and sensor-induced distortions. To overcome the challenges of data scarcity and the inability of generating high-quality pseudo-labels from corrupted images, we propose an unsupervised consistency regularization finetuning paradigm that requires only a relatively small amount of unlabeled data. Furthermore, we propose the Spatial Distance Constraint to explicitly enforce the model to learn patch-level relative relationships, resulting in clearer semantic boundaries and more accurate details. Experimental results demonstrate the zero-shot capabilities of DepthAnything-AC across diverse benchmarks, including real-world adverse weather benchmarks, synthetic corruption benchmarks, and general benchmarks. Project Page: https://ghost233lism.github.io/depthanything-AC-page Code: https://github.com/HVision-NKU/DepthAnythingAC
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。