Generative Adversarial Networks With Conditional Neural Movement Primitives For An Interactive Generative Drawing Tool

# Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool

**arXiv ID:** 2111.14934
**Authors:** Suzan Ece Ada, M. Yunus Seker
**Published:** 2021-11-29T20:20:29Z
**Abstract:**
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.

## Skill Description

This skill is generated from the arXiv paper: Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool (2111.14934).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2111.14934](http://arxiv.org/abs/2111.14934v2)