Timezone: »
The accurate exposure is the key of capturing high-quality photos in computational photography, especially for mobile phones that are limited by sizes of camera modules. Inspired by luminosity masks usually applied by professional photographers, in this paper, we develop a novel algorithm for learning local exposures with deep reinforcement adversarial learning. To be specific, we segment an image into sub-images that can reflect variations of dynamic range exposures according to raw low-level features. Based on these sub-images, a local exposure for each sub-image is automatically learned by virtue of policy network sequentially while the reward of learning is globally designed for striking a balance of overall exposures. The aesthetic evaluation function is approximated by discriminator in generative adversarial networks. The reinforcement learning and the adversarial learning are trained collaboratively by asynchronous deterministic policy gradient and generative loss approximation. To further simply the algorithmic architecture, we also prove the feasibility of leveraging the discriminator as the value function. Further more, we employ each local exposure to retouch the raw input image respectively, thus delivering multiple retouched images under different exposures which are fused with exposure blending. The extensive experiments verify that our algorithms are superior to state-of-the-art methods in terms of quantitative accuracy and visual illustration.
Author Information
Runsheng Yu (Xiaomi Intelligent Technology Co., Ltd)
Wenyu Liu (Peking University)
Yasen Zhang (Xiaomi AI Lab)
Zhi Qu (Xiaomi AI Lab)
Deli Zhao (Xiaomi AI Lab)
Bo Zhang (Xiaomi Corp.)
More from the Same Authors
-
2022 Poster: Rank Diminishing in Deep Neural Networks »
Ruili Feng · Kecheng Zheng · Yukun Huang · Deli Zhao · Michael Jordan · Zheng-Jun Zha -
2022 Spotlight: Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator »
Zifan Shi · Yinghao Xu · Yujun Shen · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Spotlight: Lightning Talks 5B-1 »
Devansh Arpit · Xiaojun Xu · Zifan Shi · Ivan Skorokhodov · Shayan Shekarforoush · Zhan Tong · Yiqun Wang · Shichong Peng · Linyi Li · Ivan Skorokhodov · Huan Wang · Yibing Song · David Lindell · Yinghao Xu · Seyed Alireza Moazenipourasil · Sergey Tulyakov · Peter Wonka · Yiqun Wang · Ke Li · David Fleet · Yujun Shen · Yingbo Zhou · Bo Li · Jue Wang · Peter Wonka · Marcus Brubaker · Caiming Xiong · Limin Wang · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Poster: Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator »
Zifan Shi · Yinghao Xu · Yujun Shen · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Poster: Improving GANs with A Dynamic Discriminator »
Ceyuan Yang · Yujun Shen · Yinghao Xu · Deli Zhao · Bo Dai · Bolei Zhou -
2021 Poster: Low-Rank Subspaces in GANs »
Jiapeng Zhu · Ruili Feng · Yujun Shen · Deli Zhao · Zheng-Jun Zha · Jingren Zhou · Qifeng Chen -
2021 Poster: RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents »
Wei Qiu · Xinrun Wang · Runsheng Yu · Rundong Wang · Xu He · Bo An · Svetlana Obraztsova · Zinovi Rabinovich -
2014 Poster: Zeta Hull Pursuits: Learning Nonconvex Data Hulls »
Yuanjun Xiong · Wei Liu · Deli Zhao · Xiaoou Tang -
2008 Poster: Cyclizing Clusters via Zeta Function of a Graph »
Deli Zhao · Xiaoou Tang