Deep reinforcement learning for image-to-image translation

X Wang, Z Luo, J Hu, C Feng, S Hu, B Zhu… - arXiv preprint arXiv …, 2023 - arxiv.org
Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of
a deep learning (DL) model. However, designing such a single-step model is always …

[PDF][PDF] Learning Object Consistency and Interaction in Image Generation from Scene Graphs.

Y Zhang, C Meng, Z Li, P Chen, G Yang, C Yang, L Sun - IJCAI, 2023 - ijcai.org
This paper is concerned with synthesizing images conditioned on a scene graph (SG), a set
of object nodes and their edges of interactive relations. We divide existing works into image …

Controlling neural style transfer with deep reinforcement learning

C Feng, J Hu, X Wang, S Hu, B Zhu, X Wu… - arXiv preprint arXiv …, 2023 - arxiv.org
Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it
usually needs hand-engineering on hyper-parameters. In this paper, we propose the first …