Metraipolis › archive › dc_3a538edfa97a
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention — arXiv:2609.24494
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24494
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:06:04.779Z
- SHA-256 of the archived text
8b5b7095bcc25070b02dd2df3794d5bfbb398e6af6ce6387e93c4a60b4ca573d- Stable URL of this page
https://metraipolis.com/documento/dc_3a538edfa97a
How to cite
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention — arXiv:2609.24494 — arXiv (en), https://arxiv.org/abs/2609.24494 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a538edfa97a (Metraipolis archive dc_3a538edfa97a, sha256 8b5b7095bcc25070b02dd2df3794d5bfbb398e6af6ce6387e93c4a60b4ca573d)
BibTeX
@misc{dc3a538edfa97a,
title = {CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention — arXiv:2609.24494},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24494},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a538edfa97a; sha256 8b5b7095bcc25070b02dd2df3794d5bfbb398e6af6ce6387e93c4a60b4ca573d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24494. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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%. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24494 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T21:45:21.051Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).