AIMDepth：面向单目深度估计的非对称图像-事件 Mamba
AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimation
把 Mamba/状态空间模型引入图像-事件跨模态融合，用线性复杂度做长序列深度估计；其「输入级先验注入 + 非对称双编码器 + 特征级对齐」的三段式融合流程，可直接迁移到其他稀疏-稠密模态配对（如 LiDAR-相机、事件-帧）的融合任务。
原文依据 we propose AIMDepth, an Asymmetric Image-Event Mamba framework for monocular depth estimation, built on state space models for linear complexity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单目深度估计对机器人等应用至关重要。事件模态与图像模态的互补特性启发了基于融合的鲁棒深度估计方法。然而，现有方法依赖卷积或基于注意力的架构，前者对长程建模的能力有限，后者计算开销高昂，因而都不太适合长序列上的深度估计。此外，有效的图像-事件融合仍然具有挑战性，因为多数方法直接融合特征，未处理原始事件与图像之间的域间差距与表征差异，导致语义偏置与性能下降。在本工作中，我们提出 AIMDepth，一个面向单目深度估计的非对称图像-事件 Mamba 框架，它构建于状态空间模型之上，具有线性复杂度并能实现准确预测。为缓解输入域的失配，我们引入频谱跨模态先验引导（SCPG），在输入层面进行双向先验注入。为减小稀疏事件与稠密图像之间的不平衡，我们设计了一个非对称模态感知编码器（AME），它采用分离的编码路径与特征级对齐。我们进一步提出模态交互式局部细化模块（ModiLocal），以实现层次化交互与细粒度对齐。在公开数据集上的实验表明，AIMDepth 在复杂环境中取得了最优性能。
英文原文摘要 1453 字符
Monocular depth estimation is essential for applications such as robotics. The complementary characteristics of event and image modalities have inspired fusion-based methods for robust depth estimation. However, existing methods rely on convolutional or attention-based architectures, which either have limited capacity for long-range modeling or incur high computational cost, making them less suitable for depth estimation over long sequences. Moreover, effective image-event fusion remains challenging, since most methods directly fuse features without addressing the domain gap and representational differences between raw events and images, resulting in semantic bias and degraded performance. In this work, we propose AIMDepth, an Asymmetric Image-Event Mamba framework for monocular depth estimation, built on state space models for linear complexity and accurate prediction. To alleviate input-domain misalignment, we introduce a Spectral Cross-modal Prior Guidance (SCPG) for bidirectional prior injection at the input level. To reduce the imbalance between sparse events and dense images, we design an asymmetric modal-aware Encoder (AME) with separate encoding paths and feature-level alignment. We further develop a Modality-interactive Local Refinement (ModiLocal) to enable hierarchical interaction and fine-grained alignment. Experiments on public datasets show that AIMDepth achieves state-of-the-art performance in complex environments.