Shape Completion Using Deep Boltzmann Machine

Abstract

Shape completion is an important task in the field of image processing. An alternative method is to capture the shape information and finish the completion by a generative model, such as Deep Boltzmann Machine. With its powerful ability to deal with the distribution of the shapes, it is quite easy to acquire the result by sampling from the model. In this paper, we make use of the hidden activation of the DBM and incorporate it with the convolutional shape features to fit a regression model. We compare the output of the regression model with the incomplete shape feature in order to set a proper and compact mask for sampling from the DBM. The experiment shows that our method can obtain realistic results without any prior information about the incomplete object shape.

Multimodal Classification on PET/CT Image Fusion for Lung Cancer: A Comprehensive Survey

“…The resultant output of the model was found to perform well with improved compression performance without limiting the details of the images 88 . In addition, RBM is adequate to work with shape distributions, which is ideal for acquiring various shapes without prior information about incomplete object shapes present in clinical images 89 . However, the drawback associated with RBM is the computational complexity and the problem with vanishing gradient, which can complicate the fusion process 90,91 .…”

Artificial Intelligence based Recommendation System for Analyzing Social Bussiness Reviews

“…4. In research [35], regression model was built using DBM to complete shapes. This network is successful in analysing heterogeneous data.…”