Depth map generation for 2D-to-3D conversion by limited user inputs and depth propagation

2011 ◽  
Author(s):  
Xi Yan ◽  
You Yang ◽  
Guihua Er ◽  
Qionghai Dai
Keyword(s):  
Depth Map ◽  
2D To 3D Conversion ◽  
Map Generation ◽  
Depth Propagation ◽  
2D To 3D

Foreground-based depth map generation for 2D-to-3D conversion

2015 ◽  
Author(s):  
Ho Sub Lee ◽  
Sung In Cho ◽  
Gyu Jin Bae ◽  
Young Hwan Kim ◽  
Hi-Seok Kim
Keyword(s):  
Depth Map ◽  
2D To 3D Conversion ◽  
Map Generation ◽  
2D To 3D

scholarly journals Real-Time 2D-to-3D Conversion for 3DTV using Time-Coherent Depth-Map Generation Method

2014 ◽  
Vol 10 (3) ◽  
pp. 9-16
Author(s):  
Seung-Woo Nam ◽  
Hye-Sun Kim ◽  
Yun-Ji Ban ◽  
Sung-Il Chien
Keyword(s):  
Real Time ◽  
Depth Map ◽  
2D To 3D Conversion ◽  
Map Generation ◽  
2D To 3D

scholarly journals Inaccuracy-Tolerant Sparse-to-Dense Depth Propagation for Semiautomatic 2D-to-3D Conversion

2018 ◽  
Vol 2018 ◽  
pp. 1-13
Author(s):  
Hongxing Yuan
Keyword(s):  
Optimization Problem ◽  
Linear Equations ◽  
Depth Map ◽  
User Input ◽  
Color Differences ◽  
2D To 3D Conversion ◽  
Different Color ◽  
3D Methods ◽  
Depth Propagation ◽  
2D To 3D

Current semiautomatic 2D-to-3D methods assume that user input is perfectly accurate. However, it is difficult to get 100% accurate user scribbles and even small errors in the input will degrade the conversion quality. This paper addresses the issue with scribble confidence that considers color differences between labeled pixels and their neighbors. First, it counts the number of neighbors which have similar and different color values for each labeled pixels, respectively. The ratio between these two numbers at each labeled pixel is regarded as its scribble confidence. Second, the sparse-to-dense depth conversion is formulated as a confident optimization problem by introducing a confident weighting data cost term and the local and k-nearest depth consistent regularization terms. Finally, the dense depth-map is obtained by solving sparse linear equations. The proposed approach is compared with existing methods on several representative images. The experimental results demonstrate that the proposed method can tolerate some errors from use input and can reduce depth-map artifacts caused by inaccurate user input.

A Depth Map Generation Algorithm Based on Saliency Detection for 2D to 3D Conversion

3D Research ◽  
2017 ◽  
Vol 8 (3) ◽  
Author(s):  
Yizhong Yang ◽  
Xionglou Hu ◽  
Nengju Wu ◽  
Pengfei Wang ◽  
Dong Xu ◽  
...  
Keyword(s):  
Saliency Detection ◽  
Depth Map ◽  
Generation Algorithm ◽  
2D To 3D Conversion ◽  
Map Generation ◽  
2D To 3D
Sign in / Sign up

Export Citation Format

Share Document