“…Recent works [55, 19,3,45,56,67,48] have demonstrated semantic manipulation, especially for facial attributes, by analyzing the manifold and finding meaningful direction or mapping. Combining with GAN inversion [1,73,2,52,64,53,4,5], the applications of 2D GANs have been extended to real image editing. Alternatively, there have been studies [11,27,36,25] that discover and disentangle latent embeddings into interpretable dimensions during training of the generator.…”