Interpreting Spatially Infinite Generative Models
@article{Lu2020InterpretingSI, title={Interpreting Spatially Infinite Generative Models}, author={Chaochao Lu and R. Turner and Yingzhen Li and Nate Kushman}, journal={ArXiv}, year={2020}, volume={abs/2007.12411} }
Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the training images, which is dictated by the number of layers in the underlying neural network. Recent work has shown, however, that feeding spatial noise vectors into a fully convolutional neural network enables both generation of arbitrary resolution output images as well as training on arbitrary resolution training images… CONTINUE READING
Figures, Tables, and Topics from this paper
References
SHOWING 1-10 OF 52 REFERENCES
Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Computer Science, Mathematics
- ICLR
- 2019
- 1,420
- Highly Influential
- PDF
Texture Synthesis with Spatial Generative Adversarial Networks
- Computer Science, Mathematics
- ArXiv
- 2016
- 99
- Highly Influential
- PDF
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Computer Science
- NIPS
- 2015
- 1,526
- Highly Influential
- PDF
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
- Computer Science, Mathematics
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 4,239
- PDF
Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
- Computer Science, Mathematics
- ICLR
- 2019
- 55
- PDF
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2019
- 370
- Highly Influential
- PDF
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
- Computer Science
- ECCV
- 2016
- 722
- PDF
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 1,291
- Highly Influential
- PDF
SinGAN: Learning a Generative Model From a Single Natural Image
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 161
- Highly Influential
- PDF
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Computer Science, Mathematics
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 1,337
- Highly Influential
- PDF