通过自适应3D体素构建，提升室内多视角3D目标检测精度与效率
Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction
- 基于几何与上下文感知模块，动态调整各视角贡献
- 稀疏体素构建策略仅保留高占位概率体素，减少冗余计算
- 仅需3D边界框即可训练，无需真实场景几何信息
本文提出SGCDet，一种基于自适应3D体素构建的多视角室内3D目标检测框架。不同于以往将体素感受野固定在图像特定位置的方法，我们引入几何与上下文感知聚合模块，在每张图像的自适应区域内融合几何与上下文信息，并动态调节不同视角的贡献，增强体素特征表示能力。此外，提出稀疏体素构建策略，自适应识别并选择高占位概率体素进行特征优化，有效减少自由空间中的冗余计算。得益于上述设计，本框架实现了高效且自适应的体素构建。更优的是，网络仅需3D边界框即可监督训练，无需依赖真实场景几何。实验表明，SGCDet在ScanNet、ScanNet200和ARKitScenes数据集上均达到领先性能。源代码已开源：https://github.com/RM-Zhang/SGCDet。
原文摘要 · Abstract (English)
This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a geometry and context aware aggregation module to integrate geometric and contextual information within adaptive regions in each image and dynamically adjust the contributions from different views, enhancing the representation capability of voxel features. Furthermore, we propose a sparse volume construction strategy that adaptively identifies and selects voxels with high occupancy probabilities for feature refinement, minimizing redundant computation in free space. Benefiting from the above designs, our framework achieves effective and efficient volume construction in an adaptive way. Better still, our network can be supervised using only 3D bounding boxes, eliminating the dependence on ground-truth scene geometry. Experimental results demonstrate that SGCDet achieves state-of-the-art performance on the ScanNet, ScanNet200 and ARKitScenes datasets. The source code is available at https://github.com/RM-Zhang/SGCDet.
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。