arXiv · 2611.19485
PALIN: Pixel-Aligned LiDAR-NIR Multimodal 3D Object Detection with Benchmark
Abstract
3D object detection is critical for intelligent transportation systems. LiDAR has been widely adopted for accurate geometric measurements; however, purely geometric representations remain ambiguous under sparse observations and occlusions, while cross-sensor multimodal fusion suffers from calibration and synchronization errors. To overcome these challenges, we leverage an Ouster LiDAR to construct PALIN (Pixel-Aligned LiDAR-NIR), a large-scale intrinsically pixel-aligned multimodal dataset jointly capturing geometry and NIR intensity, comprising approximately 8,000 annotated frames from static urban intersections and diverse mobile suburban scenes. Building upon this dataset, we propose CMambaFusion, a novel fusion framework consisting of a four-directional Cross-Mamba module for bidirectional cross-modal interaction and a Gated Concat-Mamba module for joint feature refinement. Extensive experiments demonstrate that PALIN enables effective multimodal learning, and CMambaFusion achieves superior accuracy-efficiency trade-offs over both LiDAR-only and representative fusion baselines.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yanan Zhang, Amit Vishnia, Chengbo Ai, Eleni Christofa, Runan Cheng, Siyuan Meng, Yuanchang Xie, Yu-Min, Yang. 2026-11-14. PALIN: Pixel-Aligned LiDAR-NIR Multimodal 3D Object Detection with Benchmark. https://searcharxiv.com/abs/2611.19485
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.