Institutional-Repository, University of Moratuwa.  

3D Reconstruction of objects from RGB images and depth information using deep learning

Show simple item record

dc.contributor.advisor Chithraranjan C
dc.contributor.author Karunanayaka TD
dc.date.accessioned 2022
dc.date.available 2022
dc.date.issued 2022
dc.identifier.citation Karunanayaka, T.D. (2022). 3D Reconstruction of objects from RGB images and depth information using deep learning [Master's theses, University of Moratuwa]. Institutional Repository University of Moratuwa. http://dl.lib.uom.lk/handle/123/21625
dc.identifier.uri http://dl.lib.uom.lk/handle/123/21625
dc.description.abstract Object reconstruction is the manner of producing a computer model of the 3D appearance of an object from two-dimensional photos. It's the opposite procedure of obtaining 2D photos from 3D scenes. 3D reconstruction of objects from their digital pictures is a time-efficient and convenient manner of analysing the structural features of the item being modelled. Currently there may be an essential need for 3D content for computer graphics, virtual reality and communication, triggering an alternate emphasis for the requirements. Many present methods for constructing 3D objects are built round specialized hardware resulting in a high fee, information scanning barriers due to environment conditions which can't satisfy the requirement of its new programs. The art of three-dimensional reconstruction of objects and scenes has been a broadly researched topic. In this Master’s thesis, I proposed to address the above problems by developing a Deep Learning approach to reconstruct the object. This type of approach does not depend too much on the environment condition and the cost is low. However, the proposed method mostly targets the reconstruction of objects other than reconstruction of scenes. This research attempts to develop a Deep Learning based 3D reconstruction method for objects to avoid the limitations of the current 3D reconstruction approaches. en_US
dc.language.iso en en_US
dc.subject 3D RECONSTRUCTION en_US
dc.subject RGB IMAGES en_US
dc.subject DEEP LEARNING en_US
dc.subject INFORMATION TECHNOLOGY - Dissertation en_US
dc.subject COMPUTER SCIENCE - Dissertation en_US
dc.subject COMPUTER SCIENCE & ENGINEERING - Dissertation en_US
dc.title 3D Reconstruction of objects from RGB images and depth information using deep learning en_US
dc.type Thesis-Abstract en_US
dc.identifier.faculty Engineering en_US
dc.identifier.degree MSc In Computer Science and Engineering en_US
dc.identifier.department Department of Computer Science and Engineering en_US
dc.date.accept 2022
dc.identifier.accno TH4986 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record