Neural Strokes: Stylized Line Drawing of 3D Shapes

TL;DR

This paper presents a differentiable model that generates stylized line drawings from 3D shapes, capturing artistic stroke variations and enabling vector-based outputs for editing and analysis.

Contribution

It introduces a novel geometric-based, fully differentiable approach for stylized 3D shape rendering that learns from a single drawing and preserves shape and style details.

Findings

Model produces textured, stylized line drawings from 3D shapes.

Outputs are in vector format for further editing.

Outperforms previous image-based methods in style transfer.

Abstract

This paper introduces a model for producing stylized line drawings from 3D shapes. The model takes a 3D shape and a viewpoint as input, and outputs a drawing with textured strokes, with variations in stroke thickness, deformation, and color learned from an artist's style. The model is fully differentiable. We train its parameters from a single training drawing of another 3D shape. We show that, in contrast to previous image-based methods, the use of a geometric representation of 3D shape and 2D strokes allows the model to transfer important aspects of shape and texture style while preserving contours. Our method outputs the resulting drawing in a vector representation, enabling richer downstream analysis or editing in interactive applications.