CVNov 16, 2020

Stylized Neural Painting

arXiv:2011.08114v1113 citations
AI Analysis

This addresses artistic creation for digital artists by enabling controllable, vectorized painting generation, though it is incremental as it builds on neural rendering and style transfer methods.

The paper tackles image-to-painting translation by generating vector-based stroke parameters for realistic artworks, achieving high fidelity in global appearance and local textures. It introduces a neural renderer to overcome non-differentiability and solves zero-gradient issues via optimal transport, enabling joint optimization with style transfer.

This paper proposes an image-to-painting translation method that generates vivid and realistic painting artworks with controllable styles. Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering. Since a typical vector render is not differentiable, we design a novel neural renderer which imitates the behavior of the vector renderer and then frame the stroke prediction as a parameter searching process that maximizes the similarity between the input and the rendering output. We explored the zero-gradient problem on parameter searching and propose to solve this problem from an optimal transportation perspective. We also show that previous neural renderers have a parameter coupling problem and we re-design the rendering network with a rasterization network and a shading network that better handles the disentanglement of shape and color. Experiments show that the paintings generated by our method have a high degree of fidelity in both global appearance and local textures. Our method can be also jointly optimized with neural style transfer that further transfers visual style from other images. Our code and animated results are available at \url{https://jiupinjia.github.io/neuralpainter/}.

Code Implementations4 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes