• DOI:10.1109/CVPR42600.2020.00749
Corpus ID: 209405397

SynSin: End-to-End View Synthesis From a Single Image

@article{Wiles2020SynSinEV,
  title={SynSin: End-to-End View Synthesis From a Single Image},
  author={Olivia Wiles and Georgia Gkioxari and Richard Szeliski and J. Johnson},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={7465-7475}
}

• Olivia Wiles, Georgia Gkioxari, +1 author J. Johnson
• Published 2020
• Computer Science
• 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View synthesis allows for the generation of new views of a scene given one or more images. This is challenging; it requires comprehensively understanding the 3D scene from images. As a result, current methods typically use multiple images, train on ground-truth depth, or are limited to synthetic data. We propose a novel end-to-end model for this task using a single image at test time; it is trained on real images without any ground-truth 3D information. To this end, we introduce a novel… Expand

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed