English

PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models

Computer Vision and Pattern Recognition 2022-07-12 v1 Artificial Intelligence Databases Graphics Machine Learning

Abstract

We introduce a new synthetic data generator PSP-HDRI++ that proves to be a superior pre-training alternative to ImageNet and other large-scale synthetic data counterparts. We demonstrate that pre-training with our synthetic data will yield a more general model that performs better than alternatives even when tested on out-of-distribution (OOD) sets. Furthermore, using ablation studies guided by person keypoint estimation metrics with an off-the-shelf model architecture, we show how to manipulate our synthetic data generator to further improve model performance.

Keywords

Cite

@article{arxiv.2207.05025,
  title  = {PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models},
  author = {Salehe Erfanian Ebadi and Saurav Dhakad and Sanjay Vishwakarma and Chunpu Wang and You-Cyuan Jhang and Maciek Chociej and Adam Crespi and Alex Thaman and Sujoy Ganguly},
  journal= {arXiv preprint arXiv:2207.05025},
  year   = {2022}
}

Comments

PSP-HDRI$+$ template Unity environment, benchmark binaries, and source code will be made available at: https://github.com/Unity-Technologies/PeopleSansPeople