A data driven depth estimation for 3D video conversion

Authors:
Weiyi Li;Yongjie Li;Houxiang Wang
Affiliations:
Tsinghua University, Beijing, China;University of Naval Engineer, Wuhan, China;University of Naval Engineer, Wuhan, China
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 9
Cited 0

A New Sense for Depth of Field

IEEE Transactions on Pattern Analysis and Machine Intelligence
Depth Estimation from Image Structure

IEEE Transactions on Pattern Analysis and Machine Intelligence
Depth from Scattering

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Robust analysis of feature spaces: color image segmentation

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
3D Stereoscopic Image Pairs by Depth-Map Generation

3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium
3D model comparison using spatial structure circular descriptor

Pattern Recognition
Less is More: Efficient 3-D Object Retrieval With Query View Selection

IEEE Transactions on Multimedia
Texture-adaptive hole-filling algorithm in raster-order for three-dimensional video applications

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We proposed a data driven depth estimation for automatic 2D-to-3D video conversion. First, we analyze the input video and distinguish these into the following categories: scene transition frame, non-transition frame, motion scene, static scene. After that, different 2D-to-3D conversion methods are implemented to get the depth information for that frame. The experimental results on standard testing sequences demonstrate that our scheme achieves very good 3D video quality in terms of senses of stereo, reality, and comfort.