Publications
Deep Spatial–focal Network for Depth from Focus
In this article, we propose a deep spatial–focal convolutional neural network that encodes the correlations between consecutive focused images that are fed to the network in order. In this way, our neural network understands the pattern of blur changes of each image pixel from a volumetric input of spatial–focal three-dimensional space.
[PDF]
Iterative Refinement of Uniformly Focused Image Set for Accurate Depth from Focus
Estimating the 3D shape of a scene from differently focused set of images has been a practical approach for 3D reconstruction with color cameras. However, reconstructed depth with existing DFF methods still suffer from poor quality with textureless and object boundary regions. In this paper, we propose an improved depth estimation based on UFIS...
[PDF]
Depth from Focus for 3D Reconstruction by Iteratively Building Uniformly Focused Image Set
Estimating three dimensional shape of an arbitrary object using single color is a challenging task. Depth from focus is the problem of estimating the 3 D surface of a scene from a set of two or more images of that scene. The images are obtained by changing the camera parameters and taken from the same position...
[PDF]
3D Surface Reconstruction Using Sequence of Images Based on Depth from Defocus Technique
3D surface reconstruction using Depth from Defocus(DFD) is challenging issue in Computer Vision field. Moreover, reconstruction 3D surface from single view limits information of the scene. In this paper we propose new method for 3D surface reconstruction based on DFD technique. We use several images from single viewpoint with different focus levels...
[PDF]
Small Noisy and Perspective Face Detection using Deformable Symmetric Gabor Wavelet Network
Estimating three dimensional shape of an arbitrary object using single color is a challenging task. Depth from focus is the problem of estimating the 3 D surface of a scene from a set of two or more images of that scene. The images are obtained by changing the camera parameters and taken from the same position...
[PDF]