The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years.
We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives.
We investigate two architectures for this task --- a vanilla encoder (CNN) - decoder (RNN) and another architecture that augments the encoder with an explicit memory module based on the program execution stack.
We present a framework for learning representations of 3D shapes that reflect the information present in this meta data and show that it leads to improved generalization for semantic segmentation tasks.
In this paper, we instead use efficient truncated randomized search in this reward function to train structured prediction energy networks (SPENs), which provide efficient test-time inference using gradient-based search on a smooth, learned representation of the score landscape, and have previously yielded state-of-the-art results in structured prediction.
In contrast, our model uses a recurrent neural network that parses the input shape in a top-down manner, which is significantly faster and yields a compact and easy-to-interpret sequence of modeling instructions.