Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval
This work addresses the domain-specific problem of improving 3D shape retrieval accuracy for computer graphics applications, representing an incremental advance by combining existing techniques in a novel way.
The paper tackled the problem of non-rigid 3D shape retrieval by proposing a multi-feature distance metric learning method that integrates complementary geometric information from multiple features using KL-divergence, resulting in substantial performance improvements over state-of-the-art methods on a benchmark database.
In the past decades, feature-learning-based 3D shape retrieval approaches have been received widespread attention in the computer graphic community. These approaches usually explored the hand-crafted distance metric or conventional distance metric learning methods to compute the similarity of the single feature. The single feature always contains onefold geometric information, which cannot characterize the 3D shapes well. Therefore, the multiple features should be used for the retrieval task to overcome the limitation of single feature and further improve the performance. However, most conventional distance metric learning methods fail to integrate the complementary information from multiple features to construct the distance metric. To address these issue, a novel multi-feature distance metric learning method for non-rigid 3D shape retrieval is presented in this study, which can make full use of the complimentary geometric information from multiple shape features by utilizing the KL-divergences. Minimizing KL-divergence between different metric of features and a common metric is a consistency constraints, which can lead the consistency shared latent feature space of the multiple features. We apply the proposed method to 3D model retrieval, and test our method on well known benchmark database. The results show that our method substantially outperforms the state-of-the-art non-rigid 3D shape retrieval methods.