A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of keypoints and associated appearance embeddings providing control of the position and style of the generated objects and ... We demonstrate in a user study and quantitative experiments that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging ... LatentKeypointGAN generates images with associated keypoints (a-b), which enables local editing by moving keypoints (c), exchanging appearance via the embedding we attach to each keypoint (d), removing ...arXiv:2205.03448v2 fatcat:elpenltlprci7ah4afam4erita
We show that such mask-conditioned image generation can be learned faithfully when conditioning the masks in a hierarchical manner on latent keypoints that define the position of parts explicitly. ... To address this, we propose a GAN-based approach that generates images conditioned on latent masks, thereby alleviating full or weak annotations required in previous approaches. ... Our innovation is the hierarchical generation of the image via multiple abstraction levels, including the use of masks. ...arXiv:2112.01036v2 fatcat:kjtxx3nmhrfy7cfdi5xuguhquq