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}
}
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
55 Citations
Free View Synthesis
  • 28
  • PDF
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
  • 2
  • Highly Influenced
  • PDF
Generative View Synthesis: From Single-view Semantics to Novel-view Images
  • Highly Influenced
  • PDF
Street-view Panoramic Video Synthesis from a Single Satellite Image
  • PDF
GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds
  • PDF
Generative Appearance Flow: A Hybrid Approach for Outdoor View Synthesis
  • PDF
Sequential Neural Rendering with Transformer
  • 1
Novel View Synthesis via Depth-guided Skip Connections
  • PDF
Unsupervised Continuous Object Representation Networks for Novel View Synthesis
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 85 REFERENCES
Layer-structured 3D Scene Inference via View Synthesis
  • 64
  • PDF
Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence
  • 67
  • PDF
Monocular Neural Image Based Rendering With Continuous View Control
  • 32
  • PDF
Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
  • 181
  • PDF
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
  • 121
  • Highly Influential
  • PDF
Stereo Magnification: Learning View Synthesis using Multiplane Images
  • 128
  • Highly Influential
Deep view synthesis from sparse photometric images
  • 47
  • PDF
Extreme View Synthesis
  • 45
  • PDF
...
1
2
3
4
5
...