3D video super-resolution using fully convolutional neural networks
MetadataShow full item record
SubjectConvolutional neural network (ConvNet); Virtual view; Depth map; Training; Mix-resolution; Super resolution
Large amount of redundant information and huge data size have been a serious problem for multiview video systems. To address this problem, one popular solution is mixedresolution, where only few viewpoints are kept with full resolution and other views are kept with lower resolution. In this paper, we propose a super-resolution (SR) method, where the low-resolution viewpoints in the 3D video are up-sampled using a fully convolutional neural network. By simply projecting the neighboring high resolution image to the position of the low resolution image, we learn the relationship of high and low resolution patches, and reconstruct the low resolution images into high resolution ones using the projected image information. We propose to use a fully convolutional neural network to establish a mapping between those images. The network is barely trained on 17 pairs of multiview images, and tested on other multiview images and video sequences. It is observed that our proposed method outperforms existing methods objectively and subjectively, with more than 1 dB average gain achieved. Meanwhile, our network training procedure is efficient, with less than 3 hours using one Titan X GPU.
Showing items related by title, author, creator and subject.
Jammal S; Tillo T; Xiao J (IEEE, 2017)Disparity estimation is the process of obtaining the depth information from the left and right views of a particular scene. A recent work based on convolutional neural network (CNN) has achieved state-of-the-art performance ...
Formal verification of wastewater treatment processes using events detected from continuous signals by means of artificial neural networks: Case study: SBR plant Luccarini, L; Bragadin, GL; Colombini, G; Mancini, M; Mello, P; Montali, M; Sottara, D (Elsevier, 2010)This paper proposes a modular architecture for the analysis and the validation of wastewater treatment processes. An algorithm using neural networks is used to extract the relevant qualitative patterns, such as apexes, ...
Classification of Sperm Cells According to their Chromosomic Content Using a Neural Network Trained with a Genetic Algorithm Kuri, A; Ortiz, M; Zenteno, D; Penaloza, R (IEEE-Press, 2003)A priori determination of the sex of a human individual before gestation is a desirable goal in some cases. To achieve this, it is necessary to perform the separation of sperm cells containing either X or Y chromosomes. ...