Edge-Texture-Aware Semantic Dual-Query Fusion for Multimodal 3D Object Detection
Symmetry · 02.07.2026 · 18 (7) · 1133
DOI: 10.3390/sym18071133 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 02.07.2026. Verfasst von Yuehan Wu und 4 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Natural Science Foundation of China under Grant, The Natural Science Foundation of the Inner Mongolia Autonomous Region under 498 Grant.
Abstract (Originalsprache)
Multimodal 3D object detection benefits from the complementary nature of camera images and LiDAR point clouds. However, existing voxel–pixel fusion methods typically rely on relatively coarse cross-modal interactions, which limit fine-grained structural modeling and degrade performance on small safety-critical objects. To address this issue, we propose ETA-SDQF, an edge-texture-aware semantic dual-query fusion framework designed to enhance 3D perception of vehicles, cyclists, and pedestrians. The proposed method first introduces an edge-texture-aware image backbone (ETAIB) based on the discrete wavelet transform (DWT), which improves the representation of multi-scale fine-grained image features. Then, we design a dual-query-guided attention fusion (DQGAF) module, which leverages deformable attention to adaptively aggregate voxel-aligned multi-scale image features under joint semantic and edge-texture guidance. Finally, we adopt a hybrid 3D feature learning strategy inspired by PV-RCNN, combining voxel-based feature learning with PointNet-style feature abstraction for processing fused features. This design improves the utilization of voxel features enriched with image semantics, thereby facilitating more reliable 3D object proposal generation. Experimental results on the KITTI dataset demonstrate that the proposed framework achieves better performance compared to existing baseline methods. It consistently improves pedestrian and cyclist detection, while maintaining competitive performance on car detection across different difficulty levels, showing potential benefits on challenging KITTI samples.
Förderung
- The National Natural Science Foundation of China under Grant
- The Natural Science Foundation of the Inner Mongolia Autonomous Region under 498 Grant
Zitieren
APA
Wu, Y., Zheng, Z., Liu, K., Chen, L., & Wu, R. (2026). Edge-Texture-Aware Semantic Dual-Query Fusion for Multimodal 3D Object Detection. Symmetry, 18(7), 1133. https://doi.org/10.3390/sym18071133
Vancouver
Wu Y, Zheng Z, Liu K, Chen L, Wu R. Edge-Texture-Aware Semantic Dual-Query Fusion for Multimodal 3D Object Detection. Symmetry. 2026;18(7):1133. doi:10.3390/sym18071133
BibTeX
@article{Wu2026,
author = {Wu, Yuehan and Zheng, Zheng and Liu, Kai and Chen, Leyan and Wu, Rihan},
title = {Edge-Texture-Aware Semantic Dual-Query Fusion for Multimodal 3D Object Detection},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {7},
pages = {1133},
doi = {10.3390/sym18071133}
}
EUVIMED