Hyperspherical Embedding for Point Cloud Completion

TL;DR

This paper introduces a hyperspherical embedding module for point cloud completion, normalizing embeddings to improve generalization and training stability, leading to better completion results.

Contribution

It proposes a novel hyperspherical normalization technique for embeddings, enhancing stability and performance in point cloud completion tasks.

Findings

Improved completion accuracy in experiments

More stable training with wider learning rate range

Embeddings become more compact and well-distributed

Abstract

Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often adapt an encoder-decoder architecture, where the encoder is trained to extract embeddings that are used as inputs to generate predictions from the decoder. However, the learned embeddings have sparse distribution in the feature space, which leads to worse generalization results during testing. To address these problems, this paper proposes a hyperspherical module, which transforms and normalizes embeddings from the encoder to be on a unit hypersphere. With the proposed module, the magnitude and direction of the output hyperspherical embedding are decoupled and only the directional information is optimized. We theoretically analyze the hyperspherical embedding and show that it enables more stable training with a wider range of learning rates and more compact embedding distributions. Experiment results show consistent improvement of point cloud completion in both single-task and multi-task learning, which demonstrates the effectiveness of the proposed method.