期刊
COMPUTER VISION AND IMAGE UNDERSTANDING
卷 223, 期 -, 页码 -出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.cviu.2022.103538
关键词
Computer vision; Physics based vision; Intrinsics image decomposition; Deep learning
资金
- NWO [P16-25 P2]
This study explores the intrinsic image decomposition problem, introducing physics-based priors and a new architecture to address it, and evaluates and compares the method on synthetic and real-world datasets.
Intrinsic image decomposition is the decomposition of an image into its reflectance and shading components. The intrinsic image decomposition problem is inherently ill-posed, since there can be multiple solutions to compute the intrinsic components forming the same image. In this paper, we explore the use of physics-based priors. We also propose a new architecture that separates the learning components in a stacked manner. We explore various ways of integrating such priors into a deep learning system. Our method is trained and tested on a large synthetic garden dataset to assess its performance. It is evaluated and compared to state-of-the-art methods using two standard intrinsic datasets. Finally, the pre-trained network is tested on real world images to show the generalisation capabilities of the network.
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