Viewpoint-Agnostic Image Rendering

Abstract

Rendering an any-viewpoint image is extremely difficult for Generative Adversarial Networks. This is because conventional GANs do not understand 3D information underlying a given viewpoint image such as an object shape and relationship between viewpoint and objects in 3D space. In this paper, we present how to perform a Viewpoint-Agnostic Image Rendering (VAIR), equipping a conditional GAN with a mechanism to reconstruct 3D information of the input view. VAIR realizes any-viewpoint image generation by manipulating a viewpoint in 3D space where the reconstructed instance shape is arranged. In addition, we convert the reconstructed 3D shape into a 2D representation for image-based conditional GAN, while preserving detail 3D information. The representation consists of a depth image and 2D semantic keypoint images, which are obtained by rendering the shape from a viewpoint. In the experiment, we evaluate using a CUB-200-2011 dataset, which contains few-samples biased a viewpoint such that covers only part of the target appearance. As a result, our VAIR clearly renders an any-viewpoint image.

Cite

Text

Aizawa et al. "Viewpoint-Agnostic Image Rendering." Winter Conference on Applications of Computer Vision, 2021.

Markdown

[Aizawa et al. "Viewpoint-Agnostic Image Rendering." Winter Conference on Applications of Computer Vision, 2021.](https://mlanthology.org/wacv/2021/aizawa2021wacv-viewpointagnostic/)

BibTeX

@inproceedings{aizawa2021wacv-viewpointagnostic,
  title     = {{Viewpoint-Agnostic Image Rendering}},
  author    = {Aizawa, Hiroaki and Kataoka, Hirokatsu and Satoh, Yutaka and Kato, Kunihito},
  booktitle = {Winter Conference on Applications of Computer Vision},
  year      = {2021},
  pages     = {3803-3812},
  url       = {https://mlanthology.org/wacv/2021/aizawa2021wacv-viewpointagnostic/}
}