A Global Nearest-Neighbour Depth Learning Based Automatic 2D to 3D image and Video Conversion

Abstract

Despite a significant growth in the last few years, the availability of 3D content is still dwarfed by that of its 2D counterpart. In order to close this gap, many 2D-to-3D image and video conversion methods have been proposed. Methods involving human operators have been most successful but also time-consuming and costly. Automatic methods, that typically make use of a deterministic 3D scene model, have not yet achieved the same level of quality for they rely on assumptions that are often violated in practice. The proposed work is to present a new method based on the radically different approach of learning the 2D-to-3D conversion from examples. It is based on locally estimating the entire depth map of a query image directly from a repository of 3D images (image depth pairs or stereo pairs) using a nearest-neighbour regression type idea.

Authors and Affiliations

Anusha M Sidhanti| Electronics and communications Dept VDRIT College of engineering and Technology Haliyal, India, Prof. Jyothsna C| Electronics and communications Dept VDRIT College of engineering and Technology Haliyal, India, Mounesh V M| Electronics and communications Dept VDRIT College of engineering and Technology Haliyal, India

Keywords

Related Articles

Identification of Hidden Traffic Pattern in Heuristic Approach for MANETS

Anonymous Communication is the main issue in case of MANETs. It is difficult to find the source and destination of the communication link and the other nodes involved in it. Many techniques are proposed to enhance the...

Reliable Buffer less Video Streaming

Peer-to-Peer (P2P) overlays offer a promising approach to stream live video from a single source to a large number of receivers (or peers) over the Internet without any special support from the network. This approach is...

TRANSMISSION OF DATA USING POWER LINE CARRIER COMMUNICATION SYSTEM

This paper serves as a general and technical reference to transmission of data using a power line carrier communication system which is a preferred choice over Wireless or other Home Networking technologies due to the ea...

Way-Tagged L2 Cache Architecture in Conjunction with Energy Efficient Datum Storage

For improving the performance constraint in various microprocessors write-through cache policy can be employed. However, write-through policy also incurs large energy overhead. Considering the energy factor way-tagged ca...

Conical Shape Antenna with Circular Slots for Ultra Wideband Applications

In this paper an ultra wideband of conical shaped with different configurations are designed and simulated. The antenna is printed on FR4 dielectric substrate of dimensions 42 mm X 42 mm X 1.5 mm. conical shape using as...

Download PDF file
  • EP ID EP8412
  • DOI -
  • Views 355
  • Downloads 20

How To Cite

Anusha M Sidhanti, Prof. Jyothsna C, Mounesh V M (2014). A Global Nearest-Neighbour Depth Learning Based Automatic 2D to 3D image and Video Conversion. International Journal of Electronics Communication and Computer Technology, 4(4), 701-704. https://europub.co.uk/articles/-A-8412