Metraipolis › archive › dc_d7f064fb683f
SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection — arXiv:2608.16338
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16338
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:10.215Z
- SHA-256 of the archived text
b421f8c6fec5d7816acdd49fd9bc4f26e0299756e54e5cc45ef78d83d841e841- Stable URL of this page
https://metraipolis.com/documento/dc_d7f064fb683f
How to cite
SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection — arXiv:2608.16338 — arXiv (en), https://arxiv.org/abs/2608.16338 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7f064fb683f (Metraipolis archive dc_d7f064fb683f, sha256 b421f8c6fec5d7816acdd49fd9bc4f26e0299756e54e5cc45ef78d83d841e841)
BibTeX
@misc{dcd7f064fb683f,
title = {SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection — arXiv:2608.16338},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16338},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7f064fb683f; sha256 b421f8c6fec5d7816acdd49fd9bc4f26e0299756e54e5cc45ef78d83d841e841},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16338. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurrent models, corrupted observations may enter the hidden state and produce errors that persist into later frames. Existing occlusion-aware refinements usually provide obstacle masks as auxiliary inputs, so the state-update path is only indirectly protected. We propose SIGMA-Lane, which treats this failure mode as state contamination in State Space Model (SSM)-based temporal modeling. SIGMA-Lane places occlusion-aware gates on the SSM write and residual-fusion paths, controlling how current observations enter temporal memory and are fused back after temporal propagation. After coordinate-consistent affine alignment, the model combines two complementary paths: SSM-consistent dual-gating for temporal filtering and Structural Spatial Retrieval (SSR) for recovering missing lane structure from aligned historical priors. Experiments on VIL-100 and OpenLane-V show improved temporal stability under heavy occlusion, with competitive F1 and mIoU scores. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16338 — 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 2026-10-18T16:29:14.107Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).