Research map / Point clouds / Segmentation and detection
PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection
Xuanming Shang, Weijia Zhang, Chao Ma
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add DevNet (Laplacian deviation) encoder instead of PFN max-pooling (ablation) | PointLAM LPS · nuScenes val (18-epoch ablation) | NDS: 71.42 -> 71.59 | Improved |
| add Doubly Sorted Sampling instead of pooling (ablation) | PointLAM LPS · nuScenes val (18-epoch ablation) | NDS: 71.42 -> 71.56 | Improved |
| combine DevNet and DSS (ablation) | PointLAM LPS · nuScenes val (18-epoch ablation) | NDS: 71.42 -> 71.82 | Improved |
| use Hadamard gating instead of addition (ablation) | PointLAM LHA · nuScenes val (18-epoch ablation) | NDS: 70.98 -> 71.82 | Improved |
| use Hadamard gating instead of concatenation (ablation) | PointLAM LHA · nuScenes val (18-epoch ablation) | NDS: 71.51 -> 71.82 | Improved |
| add BDM to LHA-only backbone (ablation) | PointLAM backbone · nuScenes val (18-epoch ablation) | NDS: 69.40 -> 71.82 | Improved |
| add LHA to BDM-only backbone (ablation) | PointLAM backbone · nuScenes val (18-epoch ablation) | NDS: 69.58 -> 71.82 | Improved |
| add Y-axis scan to X-axis BDM with LHA (ablation) | PointLAM BDM · nuScenes val (18-epoch ablation) | NDS: 71.23 -> 71.82 | Improved |
| use axis sort instead of random scan order (ablation) | PointLAM BDM · nuScenes val (18-epoch ablation) | NDS: 71.08 -> 71.23 | No clear effect |
| use Hilbert or Z-order curves instead of axis sort (ablation) | PointLAM BDM · nuScenes val (18-epoch ablation) | NDS: 71.23 -> 71.26 | No clear effect |
| use Laplacian-guided DSS-IS instead of random selection (ablation) | PointLAM LPS · Waymo 10% subset | L1 mAPH: 74.59 -> 75.02 | Improved |
| use transient grid instead of k-NN neighbor query (ablation) | PointLAM LHA · Waymo 10% subset | L1 mAPH: 74.61 -> 75.95 | Improved |
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.
- LION — LION: Latent Point Diffusion Models for 3D Shape Generation (NeurIPS 2022) · better on 3 of 6 shared results
- UniMamba — UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection (CVPR 2025) · better on 0 of 3 shared results
- Voxel Mamba — Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection (NeurIPS 2024) · better on 1 of 3 shared results
- HEDNet — HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds (NeurIPS 2023) · better on 2 of 2 shared results
- 3DSSD — 3DSSD: Point-Based 3D Single Stage Object Detector (CVPR 2020) · better on 1 of 1 shared result
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
- Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds (CVPR 2022 · similarity 0.91)
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (ICLR 2024 · similarity 0.89)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (AAAI 2024 · similarity 0.88)
- Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection (AAAI 2024 · similarity 0.88)
- UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.88)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.88)
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.
