天气条件感知的Depth Anything

中文摘要 AI 辅助

单目深度估计基础模型（如Depth Anything系列）在不同领域已取得显著性能，但在雾、雨、雪等恶劣天气或夜间场景下仍存在严重失效问题。为解决该问题，本文提出Weather-Conditioned Depth Anything（DA-W）框架，该框架明确解耦风格与内容以实现天气鲁棒的深度估计。具体而言，本文引入Style Filter，其在精心整理的真实与合成退化数据集混合数据上训练，用于提取与内容无关、可感知退化的天气嵌入；该风格嵌入随后通过参数高效且零初始化的适配器注入Depth Anything骨干网络。这种轻量级调制使单个统一模型能鲁棒适配雾、雨、雪、低光照等多种场景，同时避免在正常条件下核心泛化能力的灾难性遗忘。本文采用伪标签蒸馏与对齐策略训练适配器。综合实验表明，所提出的DA-W在精心整理的天气基准测试中达到最先进的鲁棒深度估计性能，AbsRel指标平均提升3.7%，同时在标准干净基准测试上的性能与原模型相当或略有超越。项目页面可通过该https URL访问。

英文摘要

Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, they still suffer from critical failures under adverse weather conditions, such as fog, rain, snow, or at night. To address this, we present Weather-Conditioned Depth Anything (DA-W), a framework that explicitly disentangles style from content for weather-robust depth estimation. Specifically, we introduce a Style Filter trained on a curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings. This style embedding is then injected into the Depth Anything backbone using a parameter-efficient, zero-initialized adapter. Such a lightweight modulation allows a single unified model to robustly adapt to diverse conditions, including fog, rain, snow, and low-light, while avoiding catastrophic forgetting of its core generalization abilities in normal conditions. We train the adapter using a pseudo-label distillation and alignment strategy. Our comprehensive experiments demonstrate that our proposed DA-W achieves state-of-the-art robust depth estimation, improving AbsRel by an average of 3.7% on our curated weather benchmarks, while matching or slightly outperforming performance on standard clean benchmarks. Our project page is available at https://zhaoming-tamu.github.io/WCDA/.

发表机构

• Texas A&M University（得克萨斯农工大学）

机构由 AI 辅助整理，请以论文原文为准。