Taming Transformers for High-Resolution Image Synthesis (a.k.a #VQGAN) Patrick Esser*, Robin Rombach*, Björn Ommer IWR, Heidelberg University CVPR 2021 (ORAL) TL;DR: We introduce the convolutional VQGAN to combine both the efficiency of convolutional approaches with the expressive power of transformers, and to combine adversarial with likelihood training in a perceptually meaningful way. The VQGAN