InstaGAN: Instance-aware Image-to-Image Translation
This work addresses a specific challenge in unsupervised image-to-image translation for computer vision applications, representing an incremental improvement over previous GAN-based methods.
The authors tackled the problem of multi-instance image-to-image translation with significant shape changes, such as converting pants to skirts in fashion images, by proposing InstaGAN, which incorporates instance segmentation masks and a context preserving loss, achieving improved performance in challenging cases.
Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when an image has multiple target instances and a translation task involves significant changes in shape, e.g., translating pants to skirts in fashion images. To tackle the issues, we propose a novel method, coined instance-aware GAN (InstaGAN), that incorporates the instance information (e.g., object segmentation masks) and improves multi-instance transfiguration. The proposed method translates both an image and the corresponding set of instance attributes while maintaining the permutation invariance property of the instances. To this end, we introduce a context preserving loss that encourages the network to learn the identity function outside of target instances. We also propose a sequential mini-batch inference/training technique that handles multiple instances with a limited GPU memory and enhances the network to generalize better for multiple instances. Our comparative evaluation demonstrates the effectiveness of the proposed method on different image datasets, in particular, in the aforementioned challenging cases. Code and results are available in https://github.com/sangwoomo/instagan