Beyond Sparsity: Receptive Field Expansion and Cross-Task Fusion for LiDAR Multi-Task Perception

LiDAR-based multi-task perception for autonomous driving requires efficient integration of spatial context and cross-task information, yet existing methods often suffer from restricted receptive fields and suboptimal task interaction. This paper presents a novel multi-task framework that goes beyond sparsity constraints, leveraging receptive field expansion and cross-task fusion to enhance 3D object detection and semantic segmentation. We introduce the Spatial Density-Invariant Multi-scale Integrator (SDIMI), which adaptively fuses multi-resolution contextual features using density-agnostic strategies to expand the receptive field while preserving feature sparsity. Additionally, the Synergistic Instance-Driven Multitask Fusion (SIDMF) module dynamically aligns instance-level features between segmentation and detection, enabling efficient high-level feature propagation via bounding box mapping masks. Experiments on NuScenes and Waymo Open Dataset demonstrate state-of-the-art performance: our method achieves 72.0% NuScenes Detection Score (NDS) and 84.4% mIOU on NuScenes, and 79.8% mAPH-L2 and 72.3% mIOU on Waymo.