SFMNet用稀疏焦点调制提升3D目标检测效率与精度
SFMNet: Sparse Focal Modulation for 3D Object Detection
- 提出稀疏焦点调制模块，线性复杂度融合局部与长程上下文
- 在Waymo和nuScenes上达到领先性能，比现有方法更快
- 适合大规模激光雷达场景的实时3D检测任务
我们提出SFMNet，一种结合稀疏卷积效率与建模长程依赖能力的新型3D稀疏检测器。传统稀疏卷积擅长捕捉局部结构，但难以建模长程关系；而基于注意力的Transformer虽能有效捕捉长程依赖，却因查询-键-值的二次复杂度导致计算开销大，且直接应用于稀疏体素效率低下。SFMNet引入一种新的稀疏焦点调制（SFM）模块，通过分层稀疏卷积设计，以线性复杂度融合短程与长程上下文信息。该方法在保持高检测性能的同时显著提升效率，适用于大规模激光雷达场景。实验表明，SFMNet在自动驾驶数据集Waymo and nuScenes上达到当前最优性能。
原文摘要 · Abstract (English)
We propose SFMNet, a novel 3D sparse detector that combines the efficiency of sparse convolutions with the ability to model long-range dependencies. While traditional sparse convolution techniques efficiently capture local structures, they struggle with modeling long-range relationships. However, capturing long-range dependencies is fundamental for 3D object detection. In contrast, transformers are designed to capture these long-range dependencies through attention mechanisms. But, they come with high computational costs, due to their quadratic query-key-value interactions. Furthermore, directly applying attention to non-empty voxels is inefficient due to the sparse nature of 3D scenes. Our SFMNet is built on a novel Sparse Focal Modulation (SFM) module, which integrates short- and long-range contexts with linear complexity by leveraging a new hierarchical sparse convolution design. This approach enables SFMNet to achieve high detection performance with improved efficiency, making it well-suited for large-scale LiDAR scenes. We show that our detector achieves state-of-the-art performance on autonomous driving datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。