A Convolutional Architecture for 3D Model Embedding

TL;DR

This paper introduces a deep learning architecture that creates meaningful vector embeddings of 3D models, improving tasks like retrieval and classification by capturing semantic information.

Contribution

It proposes a novel combination of CNNs and autoencoders to generate 3D model embeddings suitable for high-level cognitive tasks.

Findings

Embeddings effectively capture semantic features of 3D models.

Improved accuracy in 3D model retrieval tasks.

Demonstrated benefits of learned representations over traditional methods.

Abstract

During the last years, many advances have been made in tasks like3D model retrieval, 3D model classification, and 3D model segmentation.The typical 3D representations such as point clouds, voxels, and poly-gon meshes are mostly suitable for rendering purposes, while their use forcognitive processes (retrieval, classification, segmentation) is limited dueto their high redundancy and complexity. We propose a deep learningarchitecture to handle 3D models as an input. We combine this architec-ture with other standard architectures like Convolutional Neural Networksand autoencoders for computing 3D model embeddings. Our goal is torepresent a 3D model as a vector with enough information to substitutethe 3D model for high-level tasks. Since this vector is a learned repre-sentation which tries to capture the relevant information of a 3D model,we show that the embedding representation conveys semantic informationthat helps to deal with the similarity assessment of 3D objects. Our ex-periments show the benefit of computing the embeddings of a 3D modeldata set and use them for effective 3D Model Retrieval.