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 |