Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing

arXiv:2402.14398v1 Announce Type: new
Abstract: GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes. Recent inversion methods mainly utilize additional high-bit features to improve image details preservation, as low-bit codes cannot faithfully reconstruct source images, leading to the loss of details. However, during editing, existing works fail to accurately complement the lost details and suffer from poor editability. The main reason is they inject all …

abstract alignment arxiv cs.ai cs.cv editing features framework gan image images low preservation project space type