Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. However, objects in indoor scenes are usually related to each other and the scene, forming the contextual information. Based on this observation, we propose a novel 3D object detection network, which is built on the state-of-the-art VoteNet but takes into consideration of the contextual information at multiple levels for detection and recognition of 3D objects. To encode relationships between elements at different levels, we introduce three contextual sub-modules, capturing contextual information at patch, object, and scene levels respectively, and build them into the voting and classification stages of VoteNet. In addition, at the post-processing stage, we also consider the spatial diversity of detected objects and propose an improved 3D NMS (non-maximum suppression) method, namely Survival-Of-the-Best 3DNMS (SOB-3DNMS), to reduce false detections. Experiments demonstrate that our method is an effective way to promote detection accuracy, and has achieved new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet, when only taking point cloud data as input.

大多数现有的3D对象检测方法可以单独识别对象，而无需考虑这些对象之间的上下文信息。但是，室内场景中的对象通常与场景相互关联，形成上下文信息。基于此观察结果，我们提出了一种新颖的3D对象检测网络，该网络建立在最新的VoteNet之上，但考虑了用于3D对象检测和识别的多个级别的上下文信息。为了对不同级别的元素之间的关系进行编码，我们引入了三个上下文子模块，分别在补丁，对象和场景级别捕获上下文信息，并将它们构建到VoteNet的投票和分类阶段。此外，在后期处理阶段，我们还考虑了检测对象的空间多样性，并提出了一种改进的3D NMS（非最大抑制）方法，即“最佳3DNMS生存率”（SOB-3DNMS），以减少错误的检测。实验表明，我们的方法是提高检测精度的有效方法，