Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation Cabezón Pedroso, Tomás Díaz Rodríguez, Natalia Ana Deep learning Generative Adversarial Networks Automatic Design Image-to-image translation Jewelry design CycleGAN Rendering programs have changed the design process completely as they permit to see how the products will look before they are fabricated. However, the rendering process is complicated and takes a signi cant amount of time, not only in the rendering itself but in the setting of the scene as well. Materials, lights and cameras need to be set in order to get the best quality results. Nevertheless, the optimal output may not be obtained in the rst render. This all makes the rendering process a tedious process. Since Goodfellow et al. introduced Generative Adversarial Networks (GANs) in 2014 [1], they have been used to generate computer-assigned synthetic data, from non-existing human faces to medical data analysis or image style transfer. GANs have been used to transfer image textures from one domain to another. However, paired data from both domains was needed. When Zhu et al. introduced the CycleGAN model, the elimination of this expensive constraint permitted transforming one image from one domain into another, without the need for paired data. This work validates the applicability of CycleGANs on style transfer from an initial sketch to a nal render in 2D that represents a 3D design, a step that is paramount in every product design process. We inquiry the possibilities of including CycleGANs as part of the design pipeline, more precisely, applied to the rendering of ring designs. Our contribution entails a crucial part of the process as it allows the customer to see the nal product before buying. This work sets a basis for future research, showing the possibilities of GANs in design and establishing a starting point for novel applications to approach crafts design. 2022-11-22T13:21:08Z 2022-11-22T13:21:08Z 2022-07-18 info:eu-repo/semantics/conferenceObject Published version: Cabezon Pedroso, T., Ser, J.D., Díaz-Rodríguez, N. (2022). Capabilities, Limitations and Challenges of Style Transfer with CycleGANs: A Study on Automatic Ring Design Generation. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds) Machine Learning and Knowledge Extraction. CD-MAKE 2022. Lecture Notes in Computer Science, vol 13480. Springer, Cham. [https://doi.org/10.1007/978-3-031-14463-9_11] https://hdl.handle.net/10481/78078 eng http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Atribución 4.0 Internacional Springer