Disentangling Multiple Conditional Inputs in GANs
This addresses the need for precise control over generated images in fashion design, though it appears incremental as it builds on existing conditional GAN methods.
The paper tackles the problem of disentangling multiple input conditions in GANs for computer-aided fashion design, resulting in the generation of novel and realistic garment images by controlling attributes like color, texture, and shape.
In this paper, we propose a method that disentangles the effects of multiple input conditions in Generative Adversarial Networks (GANs). In particular, we demonstrate our method in controlling color, texture, and shape of a generated garment image for computer-aided fashion design. To disentangle the effect of input attributes, we customize conditional GANs with consistency loss functions. In our experiments, we tune one input at a time and show that we can guide our network to generate novel and realistic images of clothing articles. In addition, we present a fashion design process that estimates the input attributes of an existing garment and modifies them using our generator.