Text-guided human motion generation has drawn significant interest becau...
Recent large-scale text-to-image generation models have made significant...
Shape can specify key object constraints, yet existing text-to-image
dif...
Coupling the high-fidelity generation capabilities of label-conditional ...
We propose a rejection sampling scheme using the discriminator of a GAN ...
Generative Adversarial Networks (GANs) can produce images of surprising
...
In this work, we focus on the challenge of taking partial observations o...
To predict a set of diverse and informative proposals with enriched
repr...