融合图像与点云，提升3D目标检测精度。
GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
- 用自适应跨模态变换器融合图像特征增强点云语义。
- 多尺度图注意力动态建模邻近与语义关系，提升检测精度。
- 适合做3D感知系统研发或视觉-几何融合研究者参考。
尽管3D目标检测取得显著进展，点云仍因数据稀疏、结构不完整和语义信息有限而面临挑战，远距离物体间的上下文关系难以捕捉。为此，我们提出GraphFusion3D，一个统一的多模态融合与高级特征学习框架。引入自适应跨模态变换器（ACMT），将图像特征自适应融入点云表示，同时丰富几何与语义信息。为优化候选框，提出图推理模块（GRM），通过多尺度图注意力动态权衡提案间的空间接近性与特征相似性，联合建模局部几何结构与全局语义上下文。进一步采用级联解码器，通过多阶段预测逐步精炼检测结果。在SUN RGB-D（70.6% AP₂₅，51.2% AP₅₀）和ScanNetV2（75.1% AP₂₅，60.8% AP₅₀）上的大量实验表明，该方法显著优于现有方法。
原文摘要 · Abstract (English)
Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional difficulties. To address these challenges, we propose GraphFusion3D, a unified framework combining multi-modal fusion with advanced feature learning. Our approach introduces the Adaptive Cross-Modal Transformer (ACMT), which adaptively integrates image features into point representations to enrich both geometric and semantic information. For proposal refinement, we introduce the Graph Reasoning Module (GRM), a novel mechanism that models neighborhood relationships to simultaneously capture local geometric structures and global semantic context. The module employs multi-scale graph attention to dynamically weight both spatial proximity and feature similarity between proposals. We further employ a cascade decoder that progressively refines detections through multi-stage predictions. Extensive experiments on SUN RGB-D (70.6% AP$_{25}$ and 51.2% AP$_{50}$) and ScanNetV2 (75.1% AP$_{25}$ and 60.8% AP$_{50}$) demonstrate a substantial performance improvement over existing approaches.
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。