An Acceleration Framework for High Resolution Image Synthesis
By Jinlin Liu, Yuan Yao, Jianqiang Ren. 2019
10 citations recorded by the source corpus.
Synthesis of high resolution images using Generative Adversarial Networks (GANs) is challenging, which usually requires numbers of high-end graphic cards with large memory and long time of training. In this paper, we propose a two-stage framework to accelerate the training process of synthesizing high resolution images. High resolution images are first transformed to small codes via the trained encoder and decoder networks. The code in latent space is times smaller than the original high resolution images. Then, we train a code generation network to learn the distribution of the latent codes. In this way, the generator only learns to generate small latent codes instead of large images. Finally, we decode the generated latent codes to image space via the decoder networks so as to output the synthesized high resolution images. Experimental results show that the proposed method accelerates the training process significantly and increases the quality of the generated samples. The proposed acceleration framework makes it possible to generate high resolution images using less training time with limited hardware resource. After using the proposed acceleration method, it takes only 3 days to train a 1024 *1024 image generator on Celeba-HQ dataset using just one NVIDIA P100 graphic card.
Subfields: Computer Vision and Pattern Recognition, Generative Models, Efficiency & Compression
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Robin Rombach
- Björn Ommer
- Patrick Esser
- Chen Change Loy
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Andrea Vedaldi
In Generative Models
- Robin Rombach
- Patrick Esser
- Björn Ommer
- Hang Chu
- Ying Shan
- Chen Change Loy
- Andreas Blattmann
- Xintao Wang
In Efficiency & Compression
Citations in the corpus
- Taming Transformers for High-Resolution Image Synthesis (2020, background): “To improve training efficiency of Generative Adversarial Networks (GANs), [39]”
- CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation (2021, background): “Such an approach as been explored in image generation [15,36,40] and 3D shape generation [3,8].”