# Deep Learning Representation using Autoencoder for 3D Shape Retrieval

arXiv: https://arxiv.org/abs/1409.7164 · HTML: https://mlsanity.com/paper/1409.7164/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2014.

## Built on by (most cited first, 6 of 6)

- [Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval](https://mlsanity.com/paper/2202.11948/) (2022)
- [Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach](https://mlsanity.com/paper/2301.04612/) (2023)
- [Joint Triplet Autoencoder for Histopathological Colon Cancer Nuclei Retrieval](https://mlsanity.com/paper/2105.10262/) (2021)
- [Solving Inverse Problems in Stochastic Self-Organizing Systems through Invariant Representations](https://mlsanity.com/paper/2506.11796/) (2025)
- [IC classifier: a classifier for 3D industrial components based on geometric prior using GNN](https://mlsanity.com/paper/2303.05730/) (2023)
- [R3PM-Net: Real-time, Robust, Real-world Point Matching Network](https://mlsanity.com/paper/2604.05060/) (2026)

## Abstract (arXiv)

We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.