Metraipolis › archive › dc_aa975b8d0ddf
MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction — arXiv:2608.05209
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05209
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:35:48.938Z
- SHA-256 of the archived text
e5e9e8706ccbb28b467909f2d49f2895f35f05d17bad362e713ad5f174bdfe95- Stable URL of this page
https://metraipolis.com/documento/dc_aa975b8d0ddf
How to cite
MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction — arXiv:2608.05209 — arXiv (en), https://arxiv.org/abs/2608.05209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa975b8d0ddf (Metraipolis archive dc_aa975b8d0ddf, sha256 e5e9e8706ccbb28b467909f2d49f2895f35f05d17bad362e713ad5f174bdfe95)
BibTeX
@misc{dcaa975b8d0ddf,
title = {MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction — arXiv:2608.05209},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05209},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa975b8d0ddf; sha256 e5e9e8706ccbb28b467909f2d49f2895f35f05d17bad362e713ad5f174bdfe95},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Constructing reliable online HD maps remains challenging in dynamic urban environments due to moving objects and occlusions. While recent works employ feature-level temporal fusion to address this, they rely solely on per-frame ground truth supervision. Consequently, they lack an explicit objective to directly penalize the geometric noise and temporal jitter between consecutive online HD maps. To address this, we propose MapTCL, an auxiliary training strategy that formulates temporal consistency loss between current and past frames via bidirectional alignment. Specifically, Bidirectional Vector Consistency Learning (BVCL) models the geometric and semantic discrepancies between associated past and current vector instances as an auxiliary loss. We also employ Raster map Consistency Learning (RCL) as an additional loss to stabilize dense BEV features. By jointly training with these dual losses, MapTCL improves the temporal stability of generated HD maps. Extensive experiments on two standard benchmarks demonstrate the effectiveness of our approach. As a versatile plug-and-play module, MapTCL consistently enhances existing baseline models, achieving gains of +3.7 mAP & +2.8 C-mAP on nuScenes and +3.1 mAP & +2.5 C-mAP on Argoverse 2 without additional inference overhead. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05209 — 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 2026-10-31T10:23:30.960Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).