CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention

2026-09-21

AI Summary

本文提出CMambaDepth框架，通过双向通道曼巴和混合注意力模块解决单目深度估计中的跨尺度信息交互低效问题及局部与全局空间建模平衡难题。

Abstract

Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth estimation methods generally suffer from the bottleneck of inefficient cross-scale information interaction and difficulty in balancing local and global spatial modeling. In this paper, we propose CMambaDepth, a self-supervised framework that achieves efficient multi-scale feature fusion and fine-grained contextual modeling via channel-wise selective state propagation. Specifically, Bidirectional Channel Mamba (Bi-CMamba) aligns encoder features across scales and enables bidirectional information exchange among ordered scale groups. Unidirectional Channel Mamba (Uni-CMamba) progressively aggregates decoder features and retains fine-grained scale groups through a group selection mechanism for subsequent fusion. Furthermore, a Hybrid Attention Module (HAM) is introduced to combine large-kernel local context and Manhattan self-attention for complementary spatial modeling. Experimental results demonstrate that our method achieves highly competitive performance. Specifically, our model achieves an AbsRel of 0.094 and an RMSE of 4.156 on KITTI, and an AbsRel of 0.140 on DDAD. In the zero-shot cross-dataset generalization test on NYUv2, it attains an AbsRel of 0.232, outperforming the baseline RA-Depth by 7.2%.

Problem

• monocular depth estimation
• cross-scale information interaction
• spatial modeling

Innovation

• Self-supervised
• Channel Mamba
• Hybrid Attention
• Multi-scale feature fusion
• Fine-grained contextual modeling