LOD-Net: Locality-Aware 3D Object Detection Using Multi-Scale Transformer Network
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Scene Understanding3D Object DetectionResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #199 | 3D Object Detection | ScanNetV2 | Multi-Scale | mAP@0.25: 1 |
Similar Papers 제목 키워드 기반
Locality-Aware Zero-Shot Human-Object Interaction Detection
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on va…
Human-Object Interaction DetectionObjectZero-Shot Human-Object Interaction DetectionLocality-Aware Rotated Ship Detection in High-Resolution Remote Sensing Imagery Based on Multi-Scale Convolutional Network
Ship detection has been an active and vital topic in the field of remote sensing for a decade, but it is still a challenging problem due to the large scale variations, the high aspect ratios, the intensive arrangement, a…
Dual Scale-aware Adaptive Masked Knowledge Distillation for Object Detection
Recent feature masking knowledge distillation methods make use of attention mechanisms to identify either important spatial regions or channel clues for discriminative feature reconstruction. However, most of existing st…
Knowledge Distillationobject-detectionObject DetectionTransfer LearningQuantum-Inspired Tensor Network Autoencoders for Anomaly Detection: A MERA-Based Approach
We investigate whether a multiscale tensor-network architecture can provide a useful inductive bias for reconstruction-based anomaly detection in collider jets. Jets are produced by a branching cascade, so their internal…
Anomaly DetectionLATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition
Recently, 3D shape understanding has achieved significant progress due to the advances of deep learning models on various data formats like images, voxels, and point clouds. Among them, point clouds and multi-view images…
3D Object Classification3D Object Retrieval3D Shape Recognition3D Shape Retrieval+1