Orthogonal integral transform for 3D shape recognition with few examples

• Published in: The Visual computer Vol. 40; no. 5; pp. 3271 - 3284
• Main Authors: Lin, Chengde, Wang, Peng, Xiong, Shengwu, Chen, Ruyi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-05-2024; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Graphics; Computer Science; Datasets; Deep learning; Image Processing and Computer Vision; Integral transforms; Neural networks; Original Article; Orthogonality; Proteins; Semantics; Shape recognition; State-of-the-art reviews; Three dimensional models; Orthogonal integral transform; 3D invariant descriptor; Few examples; 3D shape recognition; Protein shape retrieval
• ISSN: 0178-2789; 1432-2315
• DOI: 10.1007/s00371-023-03030-6

3D shape recognition with few examples is crucial for applications involving 3D scenes, but typical methods based on surface and view suffer the failure to describe the interior and exterior features uniformly. Thus, we propose 3D orthogonal integral transform (OIT). OIT is composed of three individual integrals over a group of three orthogonal planes rotating to cover all orientations by which the volumetric shape is bisected in integrals. OIT offers the following advantages: (1) It describes a 3D shape structurally from interior to exterior uniformly, which brings about discriminative shape characteristics; and (2) the shape descriptor built on OIT is invariant with respect to translation, scaling and rotation. Furthermore, a fine-grained 3D model dataset (FGModele40) is built on ModelNet40. Experiments show that OIT can provide both discriminative and robust descriptors for 3D shape recognition with few examples. Our proposed OIT outperforms typical state-of-the-art benchmarks evaluated by the protein shape retrieval contest; additionally, it also surpasses other typical deep learning models with respect to the task of 3D shape recognition with few examples on FGModele40.