Skip to content
Conference Open access

PointLAM: Local Attentive Mamba for Efficient Point-Based 3D Object Detection

Sep 2026 · European Conference on Computer Vision · pp. 492-511 · 0 citations · 53 references
Computer Science

TL;DR

Powered by this architecture, PointLAM achieves competitive performance on nuScenes and Waymo for point-based detectors, and rivals highly optimized voxel competitors while requiring a fraction of the computational footprint.

Abstract

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/.

Read PDF

Similar papers

Conference Oct 2026

LiDAR-based 3D object detection with localization reliability enhancement based on CenterPoint

3D object detection from LiDAR point clouds is a fundamental perception task in autonomous driving, aiming to accurately localize and classify surrounding objects in sparse and irregular point-cloud data. CenterPoint is a widely adopted anchor-free baseline for LiDAR-based 3D object detection, but it often suffers from...

Jia-Wei Lin · 0 citations
Conference Open access Sep 2026

Geometry and density-aware PointPillars for lightweight 3D object detection

To address missed detections of distant sparse objects in LiDAR 3D detection and inference latency on edge devices, GD-Pillars is proposed, a lightweight algorithm that enhances local geometric descriptions and compensates for sparse target features via a log-scaled residual attention mechanism.

Yue Zhang, Qing-Hua Zeng, Fang-Dong Li et al. · 0 citations
Oct 2026

UP3D: Utilizing Pseudo Points to Enhance 3D Object Detection

LiDAR-based 3D object detection is a critical engineering component in autonomous driving systems, yet its performance is fundamentally constrained by the sparsity and range-dependent density of point clouds, especially under sparse LiDAR observations caused by increasing sensing distance. Pseudo point assisted approac...

Yu-Jian Mo, Yan Wu · 0 citations
Sep 2026

Fine-grained pillar encoder with spatial adaptation for lidar-based 3D object detection

Point clouds based object detection is a fundamental and challenge task in three-dimensional computer vision. However, existing point-based methods struggle to meet real-time object recognition requirements due to excessive raw point counts, whereas pillar-based approaches are constrained by point cloud aggregation alg...

Unknown authors · 0 citations
Sep 2026

Voxel based 3D object detection using SE attention mechanism in height domain and point cloud pseudo-completion

PH-PPC, a novel Point-Voxel based 3D object detection framework utilizing Height-Domain Attention and Point Cloud Pseudo-Completion, achieves competitive performance among voxel-based detectors and incorporates three key technical innovations to enhance robustness against occlusion.

Yuanlong Wang, Ze-Zheng Qing, Zijie Ji et al. · 0 citations
Open access Nov 2026

SP-VoxelDet: Channel-Efficient Fully Sparse 3D Object Detection via Partial Convolution

Efficient and reliable 3D perception is fundamental for autonomous robotic systems under strict onboard computational constraints. Although sparse convolution exploits spatial sparsity in LiDAR point clouds, existing methods largely overlook channel redundancy, creating unnecessary overhead on resource-limited platform...

Xing-Min Chen, X. He · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.