Abstract | ||
---|---|---|
Existing models for shape analysis directly learn feature representations on 3D point clouds. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class discrimination efficiently. In this paper, we propose a two-pronged solution to this problem that is seamlessly integrated in a single blended convolution and synthesis layer. This fully differentiable layer performs two critical tasks in succession. In the first step, it projects the input 3D point clouds into a latent 3D space to synthesize a highly compact and inter-class discriminative point cloud representation. Since, 3D point clouds do not follow a Euclidean topology, standard 2/3D convolutional neural networks offer limited representation capability. Therefore, in the second step, we propose a novel 3D convolution operator functioning inside the unit ball to extract useful volumetric features. We derive formulae to achieve both translation and rotation of our novel convolution kernels. Finally, using the proposed techniques we present an extremely light-weight, end-to-end architecture that achieves compelling results on 3D shape recognition and retrieval. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/WACV45572.2020.9093505 | 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | DocType | ISSN |
single blended convolution,input 3D point clouds,latent 3D space,inter-class discriminative point cloud representation,novel 3D convolution operator,efficient discrimination,3D shapes,inter-class discrimination,shape analysis,feature representations,irregular structure,permutation-invariant structure,Euclidean topology,standard 3D convolutional neural networks,standard 2D convolutional neural networks,unit ball,volumetric feature extraction,convolution kernels,3D shape recognition,3D shape retrieval,synthesis layer | Conference | 2472-6737 |
ISBN | Citations | PageRank |
978-1-7281-6554-7 | 0 | 0.34 |
References | Authors | |
27 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sameera Ramasinghe | 1 | 2 | 1.71 |
Salman Khan | 2 | 387 | 41.05 |
Nick Barnes | 3 | 577 | 68.68 |
Stephen Gould | 4 | 1378 | 87.70 |