RandPerson

Random 3D characters for generalizable person re-identification

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

Contributor:

Summary

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, the authors 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, they 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, the authors 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, they 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, they 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.

1.8M

Images in dataset

2020

Year Released

Key Links & Stats

RandPerson

@misc{wang2020surpassing, title={Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification}, author={Yanan Wang and Shengcai Liao and Ling Shao}, year={2020}, eprint={2006.12774}, archivePrefix={arXiv}, primaryClass={cs.CV} }

scenebox

Modalities

  1. Still Image
  2. Video

Verticals

  1. Digital Human

ML Task

  1. Object Detection
  2. Semantic Segmentation
  3. Instance Segmentation
  4. Object Recognition
  5. Object Tracking

Related organizations

Inception Institute of Artificial Intelligence (IIAI)