InfinityGAN: Towards Infinite-Resolution Image Synthesis
By Chieh Hubert Lin, Hsin-Ying Lee, Yen-Chi Cheng, Sergey Tulyakov, Ming-Hsuan Yang. 2021
19 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Generative Models
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
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Andrew Zisserman
- Bernt Schiele
In Generative Models
- Ting-Li Chen
- David J. Fleet
- Jonathan Ho
- Mohammad Norouzi
- Chitwan Saharia
- William Chan
- Tim Salimans
- Lu Jiang
Citations in the corpus
- MaskGIT: Masked Generative Image Transformer (2022, methodology): “We compare against common GAN-based baselines, including Boundless [41], In&Out [8], InfinityGAN [31], and CoModGAN [54] on extrapolating rightward with a 50% ratio.”
- Palette: Image-to-Image Diffusion Models (2021, methodology): “C.5 Evaluation and Benchmarking Details Several existing works report automated metrics such as FID, Inception Score, etc. [Kumar et al. 2021; Lin et al. 2021; Yi et al. 2020] but often lack key details such as the subset of images used for computing these metrics, or the reference distribution…”
- Improved Transformer for High-Resolution GANs (2021, background): “Recent studies [1, 13, 34, 54] explore the idea of using INRs for image generation, where they learn a hyper MLP network to predict an RGB pixel value given its coordinates on the image grid.”