Paint Transformer: Feed Forward Neural Painting with Stroke Prediction

TL;DR

The paper introduces Paint Transformer, a novel neural network that predicts stroke sets for image painting in parallel, enabling near real-time non-photo-realistic image recreation without requiring pre-existing datasets.

Contribution

It formulates neural painting as a set prediction problem and proposes a Transformer-based feed forward model trained via self-supervision, improving efficiency and generalization.

Findings

Achieves better painting quality than previous methods.

Operates in near real-time for 512x512 images.

Does not require external datasets for training.

Abstract

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement learning (RL) based agents can generate a stroke sequence step by step for this task, it is not easy to train a stable RL agent. On the other hand, stroke optimization methods search for a set of stroke parameters iteratively in a large search space; such low efficiency significantly limits their prevalence and practicality. Different from previous methods, in this paper, we formulate the task as a set prediction problem and propose a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network. This way, our model can generate a set of strokes in parallel and obtain the final painting of size 512 * 512 in near real time. More importantly, since there is no dataset available for training the Paint Transformer, we devise a self-training pipeline such that it can be trained without any off-the-shelf dataset while still achieving excellent generalization capability. Experiments demonstrate that our method achieves better painting performance than previous ones with cheaper training and inference costs. Codes and models are available.