PR-RL: Portrait Relighting Via Deep Reinforcement Learning
| Autor: | Xiaoyan Zhang, Yukai Song, Zhuopeng Li, Jianmin Jiang |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Computer science
business.industry High resolution Image editing computer.software_genre Computer Science Applications Image (mathematics) Portrait Signal Processing Media Technology Reinforcement learning Computer vision Artificial intelligence Electrical and Electronic Engineering business computer |
| Zdroj: | IEEE Transactions on Multimedia. 24:3240-3255 |
| ISSN: | 1941-0077 1520-9210 |
| Popis: | In this paper, we propose a portrait relighting method based on deep reinforcement learning (called PR-RL). Our PR-RL model could conduct portrait relighting by sequentially predicting local light editing strokes, and use strokes to conduct dodge and burn operations on the image lightness, simulating image editing by artists using brush strokes. Reinforcement learning with Deep Deterministic Policy Gradient is introduced to design our PR-RL model, defining the action (stroke parameters) in a continuous space, through which a reward can be designed to guide the agent to learn and relight a portrait image like an artist. To optimize the relighting effect, we further enable the reward to be location relevant and hence a coarse-to-fine strategy can be applied to select corresponding actions and maximize the performance of the proposed method. In comparison with the existing efforts, our proposed PR-RL method is locally effective, scale-invariant and interpretable. We apply the proposed method to tasks of portrait relighting based on both SH-lighting and reference images. The experiments show that our PR-RL method outperforms state-of-the-art methods in generating locally effective and interpretable high resolution relighting results for wild portrait images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|