To realize consistent colorization, we propose here a semi-automatic colorization method based on generative adversarial networks (GAN); the method learns the painting style of a specific comic from small amount of training data.
However, the applications of deep reinforcement learning (RL) for image processing are still limited.
This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing.
Can we detect common objects in a variety of image domains without instance-level annotations?
Ranked #1 on Weakly Supervised Object Detection on Comic2k (using extra training data)