Computer generated watch designs
One of India’s largest watchmakers uses a Deep Learning model for creating new designs for watches. The model is a Generative Adversarial Network (GAN) with added functionality to control the type of images generated by features selected by the user.
Business Impact
Improved efficiency of watch designers by helping them in their creative process.
Enabled designers to quickly visualize watch designs based on the band color, dial color, gender and band material.
Methodology
The company uses a Generative Adversarial Network (GAN) and added functionality to control the type of images generated by features selected by the user. The user can select various watch features like color of the band, color of the dial, gender and band material. This model combines human creativity with artificial intelligence to bring out the best of both. Implemented a code from scratch for the research paper – Controllable Generative Adversarial Network.