Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views

TL;DR

This paper introduces Hierarchical View Predictor (HVP), an unsupervised deep learning model that learns global 3D shape features from unordered views through hierarchical prediction, improving shape classification and retrieval performance.

Contribution

HVP is the first to perform hierarchical view prediction among unordered views for unsupervised 3D shape feature learning, effectively capturing shape structure.

Findings

Outperforms state-of-the-art methods on large-scale 3D shape benchmarks

Effective in shape classification and retrieval tasks

Learns discriminative global features from unordered views

Abstract

Unsupervised learning of global features for 3D shape analysis is an important research challenge because it avoids manual effort for supervised information collection. In this paper, we propose a view-based deep learning model called Hierarchical View Predictor (HVP) to learn 3D shape features from unordered views in an unsupervised manner. To mine highly discriminative information from unordered views, HVP performs a novel hierarchical view prediction over a view pair, and aggregates the knowledge learned from the predictions in all view pairs into a global feature. In a view pair, we pose hierarchical view prediction as the task of hierarchically predicting a set of image patches in a current view from its complementary set of patches, and in addition, completing the current view and its opposite from any one of the two sets of patches. Hierarchical prediction, in patches to patches, patches to view and view to view, facilitates HVP to effectively learn the structure of 3D shapes from the correlation between patches in the same view and the correlation between a pair of complementary views. In addition, the employed implicit aggregation over all view pairs enables HVP to learn global features from unordered views. Our results show that HVP can outperform state-of-the-art methods under large-scale 3D shape benchmarks in shape classification and retrieval.