Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification

TL;DR

This paper introduces RandPerson, a large synthetic dataset of over 1.8 million person images generated from virtual environments, which enables training models that outperform those trained on real data in person re-identification tasks.

Contribution

The authors develop a novel method to generate diverse virtual person images and demonstrate that models trained on this synthetic data generalize better than those trained on real datasets.

Findings

Models trained on RandPerson outperform real-data trained models in unseen domains.

Synthetic data can effectively replace real data for training in person re-identification.

RandPerson dataset is publicly available for research use.

Abstract

Person re-identification has seen significant advancement in recent years. However, the ability of learned models to generalize to unknown target domains still remains limited. One possible reason for this is the lack of large-scale and diverse source training data, since manually labeling such a dataset is very expensive and privacy sensitive. To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model. Specifically, we design a method to generate a large number of random UV texture maps and use them to create different 3D clothing models. Then, an automatic code is developed to randomly generate various different 3D characters with diverse clothes, races and attributes. Next, we simulate a number of different virtual environments using Unity3D, with customized camera networks similar to real surveillance systems, and import multiple 3D characters at the same time, with various movements and interactions along different paths through the camera networks. As a result, we obtain a virtual dataset, called RandPerson, with 1,801,816 person images of 8,000 identities. By training person re-identification models on these synthesized person images, we demonstrate, for the first time, that models trained on virtual data can generalize well to unseen target images, surpassing the models trained on various real-world datasets, including CUHK03, Market-1501, DukeMTMC-reID, and almost MSMT17. The RandPerson dataset is available at https://github.com/VideoObjectSearch/RandPerson.