Gu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hu Chen
Sichuan University
1 shared publication - Peng Cheng
Affiliation School of Aeronautics and Astronautics, Sichuan University, Chengdu, China
1 shared publication - Qinghua Lei
Department of Earth Sciences, Uppsala University, Uppsala, 752 36, Sweden
1 shared publication - Ting Yang
Linyi University
1 shared publication - Xiaofeng Li
Key Laboratory of Ocean Observation and Forecasting Key Laboratory of Ocean Circulation and Waves Institute of Oceanology Chinese Academy of Sciences Qingdao China
1 shared publication - Zhihui Hu
Hikvision Research Institute, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 23 February 2022
- Published by Wiley in Scientific Programming
- Vol. 2022, 1-11
Multiprojector Interreflection Compensation Using a Deep Convolution Network
The aim of multiprojector interreflection compensation is to modify input images to remove complex physical stray-light effects (interreflection) from a multiprojector immersive system. This is an important but often ignored problem, which can lead to degradation of a projection image. Traditional methods usually address this problem by computing a matrix inversion. These traditional methods often ignore issue of the clarity of the generated images. In this paper, we describe a method for learning the inversion using a deep convolutional neural network (CNN), named Superresolution Compensation Net (SRCN). SRCN consists of four convolution layers to learn interactions of global light, six convolution layers, and two transposed convolution layers to extract multilevel features and generate compensation images. We also used a subpixel convolution layer to increase the resolution. To make compensation images more consistent with human visual perception, we used a perceptual loss, which compares the differences between feature maps on the VGG16 network. We implemented an immersive projector-camera display prototype (Pro-Cam) and calculated the quality index of the compensation images and the projection results. Our method achieved better results than previous methods in both objective evaluations and subjective visual perception.
- 23 February 2022
- Published by Wiley in Scientific Programming
- Vol. 2022, 1-11
Open AccessMultiprojector Interreflection Compensation Using a Deep Convolution Network
The aim of multiprojector interreflection compensation is to modify input images to remove complex physical stray-light effects (interreflection) from a multiprojector immersive system. This is an important but often ignored problem, which can lead to degradation of a projection image. Traditional methods usually address this problem by computing a matrix inversion. These traditional methods often ignore issue of the clarity of the generated images. In this paper, we describe a method for learning the inversion using a deep convolutional neural network (CNN), named Superresolution Compensation Net (SRCN). SRCN consists of four convolution layers to learn interactions of global light, six convolution layers, and two transposed convolution layers to extract multilevel features and generate compensation images. We also used a subpixel convolution layer to increase the resolution. To make compensation images more consistent with human visual perception, we used a perceptual loss, which compares the differences between feature maps on the VGG16 network. We implemented an immersive projector-camera display prototype (Pro-Cam) and calculated the quality index of the compensation images and the projection results. Our method achieved better results than previous methods in both objective evaluations and subjective visual perception.