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

arXiv:2604.16696v1 Announce Type: new Abstract: 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.

Related

• Fed3D: Federated 3D Object Detection
• TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
• Multi-Agent Object Detection Framework Based on Raspberry Pi YOLO Detector and Slack-Ollama Natural Language Interface
• Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval
• Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction

Source: arXiv cs.CV | 2026-04-21