期刊
ACM TRANSACTIONS ON GRAPHICS
卷 37, 期 4, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3197517.3201313
关键词
Image-based relighting; Illumination; Convolutional Neural Network; Sparse sampling; Appearance capture
资金
- NSF [1451830, 1703957]
- Adobe
- Powell Bundle Fellowship
- UC San Diego Center for Visual Computing
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1451830, 1703957] Funding Source: National Science Foundation
We present an image-based relighting method that can synthesize scene appearance under novel, distant illumination from the visible hemisphere, from only five images captured under pre-defined directional lights. Our method uses a deep convolutional neural network to regress the relit image from these five images; this relighting network is trained on a large synthetic dataset comprised of procedurally generated shapes with real-world reflectances. We show that by combining a custom-designed sampling network with the relighting network, we can jointly learn both the optimal input light directions and the relighting function. We present an extensive evaluation of our network, including an empirical analysis of reconstruction quality, optimal lighting configurations for different scenarios, and alternative network architectures. We demonstrate, on both synthetic and real scenes, that our method is able to reproduce complex, high-frequency lighting effects like specularities and cast shadows, and outperforms other image-based relighting methods that require an order of magnitude more images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据