We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner.
Ranked #1 on Image Generation on FFHQ-U
We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines.
We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5. 59 to 2. 42.
Ranked #1 on Image Generation on FFHQ 1024 x 1024
Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
Ranked #1 on Image Generation on FFHQ