Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6450-6458
DOI: 10.1609/aaai.v40i8.37573 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wei Li und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Accurate reconstruction of 3D vehicle pose and shape from monocular images is challenging, particularly for distant objects in autonomous driving. Existing methods often suffer from geometric ambiguity in depth estimation and structural hollowness in shape recovery, primarily due to inadequate multi-scale feature aggregation and unflexible prior modeling. To overcome these limitations, MonoVPR is proposed, a novel framework integrating dynamic context adaptation and progressive geometry refinement. Specifically, a Hierarchical Dual-Context Attention (HDCA) module is introduced to resolve scale-dependent degradation through gated cross-attention across multi-resolution feature maps, dynamically fusing object-centric geometric cues with scene-centric semantics. For shape refinement, the Bounded Iterative Mesh Refiner (BIMR) progressively optimizes template-guided deformations via multi-head attention and a tanh-bounded correction loop, ensuring physically plausible reconstructions.Extensive experiments on the ApolloCar3D benchmark demonstrate MonoVPR achieves state-of-the-art performance, showing exceptional capability in reconstructing geometrically consistent shapes and precise poses for challenging long-range scenarios.
Zitieren
APA
Li, W., Ji, L., Wang, Y., Wu, X., Yuan, Z., & Dai, P. (2026). Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6450-6458. https://doi.org/10.1609/aaai.v40i8.37573
Vancouver
Li W, Ji L, Wang Y, Wu X, Yuan Z, Dai P. Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6450-6458. doi:10.1609/aaai.v40i8.37573
BibTeX
@article{Li2026,
author = {Li, Wei and Ji, Long and Wang, Ying and Wu, Xiao and Yuan, Zhaoquan and Dai, Penglin},
title = {Monocular Vehicle Pose and Shape Reconstruction via Dynamic Context Adaptation and Progressive Geometry Refinement},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6450--6458},
doi = {10.1609/aaai.v40i8.37573}
}
EUVIMED