Large-Scale Shape Retrieval with Sparse 3D Convolutional Neural Networks
This work addresses efficient 3D shape analysis for computer vision applications, but it is incremental as it builds on existing sparse CNN methods.
The paper tackled 3D shape retrieval by evaluating Sparse 3D Convolutional Neural Networks (S3DCNN) on ModelNet40, showing comparable performance to state-of-the-art models with significantly reduced computational costs, and noting that higher voxel resolution may not always improve generalization.
In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a large-scale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape. We demonstrate comparable classification and retrieval performance to state-of-the-art models, but with much less computational costs in training and inference phases. We also notice that benefits of higher input resolution can be limited by an ability of a neural network to generalize high level features.