AI Paper Atlas

Research map / Point clouds / Segmentation and detection

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

Xuanming Shang, Weijia Zhang, Chao Ma

ECCV 2026 · Point clouds › Segmentation and detection · approach: LiDAR voxel and pillar detectors · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DevNet (Laplacian deviation) encoder instead of PFN max-pooling (ablation)PointLAM LPS · nuScenes val (18-epoch ablation)NDS: 71.42 -> 71.59Improved
add Doubly Sorted Sampling instead of pooling (ablation)PointLAM LPS · nuScenes val (18-epoch ablation)NDS: 71.42 -> 71.56Improved
combine DevNet and DSS (ablation)PointLAM LPS · nuScenes val (18-epoch ablation)NDS: 71.42 -> 71.82Improved
use Hadamard gating instead of addition (ablation)PointLAM LHA · nuScenes val (18-epoch ablation)NDS: 70.98 -> 71.82Improved
use Hadamard gating instead of concatenation (ablation)PointLAM LHA · nuScenes val (18-epoch ablation)NDS: 71.51 -> 71.82Improved
add BDM to LHA-only backbone (ablation)PointLAM backbone · nuScenes val (18-epoch ablation)NDS: 69.40 -> 71.82Improved
add LHA to BDM-only backbone (ablation)PointLAM backbone · nuScenes val (18-epoch ablation)NDS: 69.58 -> 71.82Improved
add Y-axis scan to X-axis BDM with LHA (ablation)PointLAM BDM · nuScenes val (18-epoch ablation)NDS: 71.23 -> 71.82Improved
use axis sort instead of random scan order (ablation)PointLAM BDM · nuScenes val (18-epoch ablation)NDS: 71.08 -> 71.23No clear effect
use Hilbert or Z-order curves instead of axis sort (ablation)PointLAM BDM · nuScenes val (18-epoch ablation)NDS: 71.23 -> 71.26No clear effect
use Laplacian-guided DSS-IS instead of random selection (ablation)PointLAM LPS · Waymo 10% subsetL1 mAPH: 74.59 -> 75.02Improved
use transient grid instead of k-NN neighbor query (ablation)PointLAM LHA · Waymo 10% subsetL1 mAPH: 74.61 -> 75.95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 5 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy