mlsanityData to 7 Oct 2026

LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network

arXiv 2604.16696 ↗First posted 17 Apr 2026cs.CV cs.AI eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR architecture to better capture both local geometry and global context. Our method introduces an upsampling operation that generates high-resolution feature maps, enabling the network to better detect smaller and semantically related objects. Experiments conducted on the ScanNetv2 dataset demonstrate that our 3DETR + MSA model improves detection performance, achieving a gain of almost 1% in mAP@25 and 4.78% in mAP@50 over the baseline. While applying MSA to the 3DETR-m variant shows limited improvement, our analysis reveals the importance of adapting the upsampling strategy for lightweight models. These results highlight the effectiveness of combining hierarchical feature extraction with attention mechanisms in enhancing 3D scene understanding.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 17 Apr 2026.

Builds on

25 of 35 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2020PCT: Point cloud transformercited by 730
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  7. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  8. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  9. 2021Group-Free 3D Object Detection via Transformerscited by 215
  10. 20203D Object Detection with Pointformercited by 194
  11. 2018Scan2CAD: Learning CAD Model Alignment in RGB-D Scanscited by 142
  12. 20203D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentationcited by 140
13 more
  1. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  2. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  3. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  4. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  5. 2020Generative Sparse Detection Networks for 3D Single-shot Object Detectioncited by 69
  6. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  7. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  8. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  9. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  10. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  11. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  12. 2018Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Weldingcited by 14
  13. 2020Point Transformercited by 1

Built on by

Not cited yet.