The Hong Kong University of Science and Technology

Microsoft Technology Licensing, LLC

Long Quan

Peng Zhao

Tian Fang

Jian Qiao Sun

Heung-Yeung Shum

Lu Yuan

Honghui Zhang

Jianxiong Xiao

Systems and methods are provided to facilitate architectural modeling. In one aspect, a modeling system is provided. This includes a processor configured to generate remodeled images associated with one or more architectural structures. A procedural model is configured to integrate an approximate model from aerial images of the architectural structures and a three-dimensional (3D) reconstruction model from ground-level images of the architectural structures.

Image-based procedural remodeling of buildings

The subject disclosure relates to generating three-dimensional fa&#xe7;ade models from images. In one aspect, a systematic decomposition schema is disclosed for a fa&#xe7;ade structured into a Direct Acyclic Graph and implemented as a top-down recursive subdivision and bottom-up merging. In a further aspect, optimization of fa&#xe7;ade depth operating in a fa&#xe7;ade surface and in the super-pixel level of a whole subdivision region is described.

Generating three-dimensional fa&#xe7;ade models from images

Systems and methods are provided to facilitate architectural modeling. In one aspect, repetitive patterns are automatically detected and analyzed to generate modeled structural images such as building facades. In another aspect, structural symmetry is analyzed to facilitate architectural modeling and enhanced image generation.

Architectural pattern detection and modeling in images

The subject disclosure relates to generating models from images. In an aspect, multi-view semantic segmentation is provided to recognize and segment images at the pixel level into semantically meaningful areas, and which can provide labels with a specific object class. In further aspects, a partition scheme is provided that can separate objects into independent blocks using major line structures of a scene. In addition, an inverse patch-based orthographic composition and structure analysis on a block is provided that can regularize noisy and missing reconstructed 3D data to facilitate image-based modeling.

Generating three-dimensional models from images

Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.

Removing blur from an image

Systems, methods, and apparatus are described that that increase computer vision analysis in the field of semantic segmentation. With images accompanied by scan data, both two-dimensional and three-dimensional image information is employed for joint segmentation. Through the established correspondence between image data and scan data, two-dimensional and three-dimensional information respectively associated therewith is integrated. Using trained random forest classifiers, the probability of each pixel in images belonging to different object classes is predicted. With the predicted probability, optimization of the labeling of images and scan data is performed by integrating multiples cues in the markov random field.

Growing community of inventors

Hong Kong, China

Long Quan