Always Clear Depth：恶劣天气下的鲁棒单目深度估计
Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather
- Harbin Institute of Technology（哈尔滨工业大学）
- Dalian Maritime University（大连海事大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对恶劣天气下单目深度估计性能下降的问题，提出ACDepth方法，通过扩散模型生成退化训练数据结合多粒度知识蒸馏策略，提升了恶劣天气下的深度估计精度。
AI中文摘要：
单目深度估计对自动驾驶、场景重建等应用至关重要。现有方法在正常场景下表现良好，但在恶劣天气中会因域偏移挑战和场景信息提取困难出现性能下降。为解决该问题，我们从高质量训练数据生成与域适应的角度出发，提出了名为ACDepth的鲁棒单目深度估计方法。具体而言，我们引入一步扩散模型生成模拟恶劣天气条件的样本，在训练过程中构建多元退化数据集。为保证生成的退化样本质量，我们采用LoRA适配器微调扩散模型的生成权重，同时结合循环一致性损失与对抗训练，保障场景内容的保真度与自然度。此外，我们设计了多粒度知识蒸馏策略（MKD），促使学生网络同时从教师模型和预训练的Depth Anything V2中吸收知识，引导学生模型从各类退化输入中学习与退化无关的场景信息。我们还特别引入了序数引导蒸馏机制（OGD），通过差异排序促使网络关注不确定区域，实现更精准的深度估计。实验结果表明，在nuScenes数据集上，我们的ACDepth在absRel指标上，夜景场景优于md4all-DD 2.50%，雨天场景优于md4all-DD 2.61%。
英文摘要：
Monocular depth estimation is critical for applications such as autonomous driving and scene reconstruction. While existing methods perform well under normal scenarios, their performance declines in adverse weather, due to challenging domain shifts and difficulties in extracting scene information. To address this issue, we present a robust monocular depth estimation method called \textbf{ACDepth} from the perspective of high-quality training data generation and domain adaptation. Specifically, we introduce a one-step diffusion model for generating samples that simulate adverse weather conditions, constructing a multi-tuple degradation dataset during training. To ensure the quality of the generated degradation samples, we employ LoRA adapters to fine-tune the generation weights of diffusion model. Additionally, we integrate circular consistency loss and adversarial training to guarantee the fidelity and naturalness of the scene contents. Furthermore, we elaborate on a multi-granularity knowledge distillation strategy (MKD) that encourages the student network to absorb knowledge from both the teacher model and pretrained Depth Anything V2. This strategy guides the student model in learning degradation-agnostic scene information from various degradation inputs. In particular, we introduce an ordinal guidance distillation mechanism (OGD) that encourages the network to focus on uncertain regions through differential ranking, leading to a more precise depth estimation. Experimental results demonstrate that our ACDepth surpasses md4all-DD by 2.50\% for night scene and 2.61\% for rainy scene on the nuScenes dataset in terms of the absRel metric.
