Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool
This work addresses sketch generation for interactive drawing tools, but it appears incremental as it builds upon existing methods with a novel loss.
The authors tackled the problem of generating smooth and consistent sketches by proposing GAN-CNMP, a framework that incorporates an adversarial loss on Conditional Neural Movement Primitives, resulting in improved shape consistency and smoothness compared to the base model.
Sketches are abstract representations of visual perception and visuospatial construction. In this work, we proposed a new framework, Generative Adversarial Networks with Conditional Neural Movement Primitives (GAN-CNMP), that incorporates a novel adversarial loss on CNMP to increase sketch smoothness and consistency. Through the experiments, we show that our model can be trained with few unlabeled samples, can construct distributions automatically in the latent space, and produces better results than the base model in terms of shape consistency and smoothness.