A novel Complementary Dual-aware Network for point cloud classification

As an elementary research, three-dimensional (3D) point cloud classification study can further serve high-level downstream applications such as 3D reconstruction, generation, and completion. Recently, excellent performance for synthetic point cloud data classification have achieved, but most of them do not work well on point cloud shape collected from real-world scenarios due to its complexity with noises, varies background, occlusion, etc. As we all known, human can handle it easily. Thus, this paper proposed a Complementary Dual-aware Network (ComDa-Net) inspired by the neurobiological basis of human visual system, aiming to enhance the ability of perceiving 3D objects in real-world scenarios. Specifically, the Essential Perceived Unit (EPU) is proposed to realize the primary complementary dual-aware mechanism through elaborated variational resolutions and receptive fields, then multiple EPUs stack to form the cross-complemented hierarchical system. The proposed method achieves advanced and stable accuracy on the wild-used real-world point cloud benchmarks, and its efficiency in terms of computational and storage is also satisfied, which validates the proposed method’s expected performances. In addition, the proposed method also achieves competitive performance on the synthetic point cloud benchmarks.