Breaking Down Monocular Ambiguity: Exploiting Temporal Evolution for 3D Lane Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911248836198400 |
|---|---|
| author | Zheng, Huan Han, Wencheng Yan, Tianyi Xu, Cheng-zhong Shen, Jianbing |
| author_facet | Zheng, Huan Han, Wencheng Yan, Tianyi Xu, Cheng-zhong Shen, Jianbing |
| contents | Monocular 3D lane detection aims to estimate the 3D position of lanes from frontal-view (FV) images. However, existing methods are fundamentally constrained by the inherent ambiguity of single-frame input, which leads to inaccurate geometric predictions and poor lane integrity, especially for distant lanes. To overcome this, we propose to unlock the rich information embedded in the temporal evolution of the scene as the vehicle moves. Our proposed Geometry-aware Temporal Aggregation Network (GTA-Net) systematically leverages the temporal information from complementary perspectives. First, Temporal Geometry Enhancement Module (TGEM) learns geometric consistency across consecutive frames, effectively recovering depth information from motion to build a reliable 3D scene representation. Second, to enhance lane integrity, Temporal Instance-aware Query Generation (TIQG) module aggregates instance cues from past and present frames. Crucially, for lanes that are ambiguous in the current view, TIQG innovatively synthesizes a pseudo future perspective to generate queries that reveal lanes which would otherwise be missed. The experiments demonstrate that GTA-Net achieves new SoTA results, significantly outperforming existing monocular 3D lane detection solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Breaking Down Monocular Ambiguity: Exploiting Temporal Evolution for 3D Lane Detection Zheng, Huan Han, Wencheng Yan, Tianyi Xu, Cheng-zhong Shen, Jianbing Computer Vision and Pattern Recognition Monocular 3D lane detection aims to estimate the 3D position of lanes from frontal-view (FV) images. However, existing methods are fundamentally constrained by the inherent ambiguity of single-frame input, which leads to inaccurate geometric predictions and poor lane integrity, especially for distant lanes. To overcome this, we propose to unlock the rich information embedded in the temporal evolution of the scene as the vehicle moves. Our proposed Geometry-aware Temporal Aggregation Network (GTA-Net) systematically leverages the temporal information from complementary perspectives. First, Temporal Geometry Enhancement Module (TGEM) learns geometric consistency across consecutive frames, effectively recovering depth information from motion to build a reliable 3D scene representation. Second, to enhance lane integrity, Temporal Instance-aware Query Generation (TIQG) module aggregates instance cues from past and present frames. Crucially, for lanes that are ambiguous in the current view, TIQG innovatively synthesizes a pseudo future perspective to generate queries that reveal lanes which would otherwise be missed. The experiments demonstrate that GTA-Net achieves new SoTA results, significantly outperforming existing monocular 3D lane detection solutions. |
| title | Breaking Down Monocular Ambiguity: Exploiting Temporal Evolution for 3D Lane Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.20525 |