发表机构
Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PointLAM提出拉普拉斯点采样器和局部哈达玛聚合器，结合双向Mamba，实现高效且强大的基于点三维物体检测，在nuScenes和Waymo上以低计算成本达到与体素方法相当的性能。
AI 中文摘要
从LiDAR点云进行三维物体检测面临一个基本困境：基于体素的方法以几何量化为代价实现效率，而基于点的方法保持保真度但遭受高昂的计算瓶颈。具体而言，基于点的架构因缓慢的下采样策略（如FPS）和昂贵的动态邻居查询（如k-NN）以及代价高昂的连续交互而受到严重制约。为解决这些系统性低效问题，我们提出PointLAM，一种由两项协同创新驱动的高效且强大的基于点架构。首先，为解决下采样瓶颈，我们开发了拉普拉斯点采样器（LPS）。LPS采用隐式离散拉普拉斯高通滤波器和双重排序采样，实现快速、结构感知的前景保留。其次，为克服局部建模延迟，我们设计了局部哈达玛聚合器（LHA）。LHA使用瞬态网格将空间索引与特征表示解耦，并用哈达玛门控机制替代复杂的连续交互，实现拓扑感知的注意力调制。通过将此局部门控与双向Mamba（BDM）层耦合以进行全局序列建模，我们构建了局部注意力Mamba（LAM）块。凭借此架构，PointLAM在nuScenes和Waymo上为基于点的检测器实现了具有竞争力的性能。它可与高度优化的基于体素的竞争对手相媲美，同时仅需一小部分计算开销，在检测小物体和处理极端稀疏性方面表现出显著优势。项目页面：此https URL。
英文摘要
3D object detection from LiDAR point clouds faces a fundamental dilemma: voxel-based methods achieve efficiency at the cost of geometric quantization, while point-based methods preserve fidelity but suffer from prohibitive computational bottlenecks. Specifically, point-based architectures are crippled by slow downsampling strategies (e.g., FPS) and expensive dynamic neighbor queries (e.g., k-NN) coupled with costly continuous interactions. To tackle these systemic inefficiencies, we propose PointLAM, a highly efficient and powerful point-based architecture driven by two synergistic innovations. First, to resolve the downsampling bottleneck, we develop the Laplacian Point Sampler (LPS). LPS employs an implicit discrete Laplacian high-pass filter and Doubly Sorted Sampling to achieve fast, structure-aware foreground preservation. Second, to overcome local modeling latency, we design the Local Hadamard Aggregator (LHA). LHA decouples spatial indexing from feature representation using transient grids, and replaces complex continuous interactions with a Hadamard Gating mechanism for topology-aware, attentive modulation. By coupling this local gating with Bi-Directional Mamba (BDM) layers for global sequence modeling, we formulate the Local Attentive Mamba (LAM) block. Powered by this architecture, PointLAM achieves competitive performance on nuScenes and Waymo for point-based detectors. It rivals highly optimized voxel competitors while requiring a fraction of the computational footprint, demonstrating marked superiority in detecting small instances and handling extreme sparsity. Project page: https://pointlam.github.io/.
CommentsAccepted to ECCV 2026
