Parallel Generative Adversarial Network for Third-Person to First-Person Image Generation

Abstract

Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate third-person (exocentric) view to first-person (egocentric) view image generation. This is a challenging task since egocentric view sometimes is remarkably different from exocentric view. Thus, transforming the appearances across the two views is a non-trivial task. To this end, we propose a novel Parallel Generative Adversarial Network (P-GAN) with a novel cross-cycle loss to learn the shared information for generating egocentric images from exocentric view. We also incorporate a novel contextual feature loss in the learning procedure to capture the contextual information in images. Extensive experiments on the Exo-Ego datasets [5] show that our model outperforms the state-of-the-art approaches.

Cite

Text

Liu et al. "Parallel Generative Adversarial Network for Third-Person to First-Person Image Generation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00208

Markdown

[Liu et al. "Parallel Generative Adversarial Network for Third-Person to First-Person Image Generation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/liu2022cvprw-parallel/) doi:10.1109/CVPRW56347.2022.00208

BibTeX

@inproceedings{liu2022cvprw-parallel,
  title     = {{Parallel Generative Adversarial Network for Third-Person to First-Person Image Generation}},
  author    = {Liu, Gaowen and Latapie, Hugo and Kiliç, Özkan and Lawrence, Adam},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2022},
  pages     = {1916-1922},
  doi       = {10.1109/CVPRW56347.2022.00208},
  url       = {https://mlanthology.org/cvprw/2022/liu2022cvprw-parallel/}
}