# Shape retrieval of non-rigid 3d human models

arXiv: https://arxiv.org/abs/2003.08763 · HTML: https://mlsanity.com/paper/2003.08763/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [A Graph Encoder-Decoder Network for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2308.07774/) (2023)
- [Classification of developmental and brain disorders via graph convolutional aggregation](https://mlsanity.com/paper/2311.07370/) (2023)
- [A Class of Topological Pseudodistances for Fast Comparison of Persistence Diagrams](https://mlsanity.com/paper/2402.14489/) (2024)
- [Canonical Pose Reconstruction from Single Depth Image for 3D Non-rigid Pose Recovery on Limited Datasets](https://mlsanity.com/paper/2505.17992/) (2025)

## Abstract (arXiv)

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods.