Methods, apparatus and systems incorporating gans minimizing attribute entanglement using self-corrected gans spaces

Abstract

Methods, apparatus, systems achieve disentanglement in semantic editing using GANs-based models. Self-corrected (low-density) latent code samples are projected in the original latent space and the editing directions corrected though relearning based on resulting high-density and low-density regions in the amended latent space. Leveraging the original meaningful directions and semantic region-specific layers, operations interpolate the original latent codes to generate images with minority combinations of attributes, then inverts these samples back to the original latent space. In accordance with embodiments, the operations can apply to preexisting methods that learn meaningful latent directions. Attribute disentanglement is improved with small amounts of low-density region samples added. Resulting GANs models with disentangled editing directions are useful in a variety of applications including virtual reality applications, virtual try on (VTO) applications or other virtual try out applications that simulate an effect of a product or service, among other applications.