Learning Robust Point Representation for 3D Non-Rigid Shape Retrieval

Content-based 3D object retrieval is a challenging problem in computer vision and graphics, especially for non-rigid 3D shapes. This article proposes a multiview-based robust point representation approach for 3D non-rigid shape retrieval. First, we propose an efficient local descriptor called the local point histogram, which is robust to non-rigid changes in shape. Second, we encode local point histogram features into high-level point features (HPF) using Fisher vectors. Finally, we present an efficient feature fusion method that can further enhance the performance of 3D non-rigid shape retrieval. We extensively tested our approach on two benchmark 3D non-rigid shape datasets, including the SHREC2015 non-rigid shape and SHREC2015 canonical forms. Our method achieves 98.33% and 90.55% retrieval accuracy on the SHREC2015 non-rigid shape and SHREC2015 canonical forms datasets, surpassing previous state-of-the-art methods by nearly 2% and 7%, respectively. In addition, we further tested our method on the well-known 3D rigid shape dataset ModelNet, and the experimental results demonstrate that our method is also effective for 3D rigid shape retrieval. We also combine the proposed HPF shape features with deep convolutional features for the 3D rigid shape retrieval task, achieving a retrieval performance comparable to the prior state-of-the-art methods, which indicates a strong complementarity between HPF shape features and deep convolutional features.