GANgealing: GAN-Supervised Dense Visual Alignment


GANgealing: GAN-Supervised Dense Visual Alignment

GAN-Supervised Dense Visual Alignment

“We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense visual alignment problem. Inspired by the classic Congealing method, our GANgealing algorithm trains a Spatial Transformer to warp random samples from a GAN trained on unaligned data to a common, jointly-learned target mode. The target mode is updated to make the Spatial Transformer’s job “as easy as possible.”

GANgealing significantly outperforms past self-supervised correspondence algorithms and performs on-par with (and sometimes exceeds) state-of-the-art supervised correspondence algorithms on several datasets—without making use of any correspondence supervision or data augmentation and despite being trained exclusively on GAN-generated data. For precise correspondence, we improve upon state-of-the-art supervised methods by as much as 3x…”


April 21, 2022
Inline Feedbacks
View all comments

Subscribe to our Digest