2D to 3d image conversion based on classification of background depth profiles

Authors:
Guo-Shiang Lin;Han-Wen Liu;Wei-Chih Chen;Wen-Nung Lie;Sheng-Yen Huang
Affiliations:
Dept. of Computer Science and Information Engineering, Da-Yeh University, Chang-Hua, Taiwan, R.O.C.;Department of Electrical Engineering, National Chung Cheng University, Chia-Yi, Taiwan, R.O.C.;Department of Electrical Engineering, National Chung Cheng University, Chia-Yi, Taiwan, R.O.C.;Department of Electrical Engineering, National Chung Cheng University, Chia-Yi, Taiwan, R.O.C.;Reallusion Inc., New Taipei City, Taiwan
Venue:
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part II
Year:
2011

Citing 6
Cited 0

Shape from Focus

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bilateral Filtering for Gray and Color Images

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Segmentation of Color Images using Mean Shift Algorithm for Feature Extraction

ICIT '06 Proceedings of the 9th International Conference on Information Technology
A Shape Feature Extraction Method Based on 3D Convolution Masks

ISM '06 Proceedings of the Eighth IEEE International Symposium on Multimedia
Automatic depth profiling of 2D cinema- and photographic images

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Object-Based stereoscopic conversion of MPEG-4 encoded data

PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a 2D to 3D stereo image conversion scheme is proposed for 3D content creation. The difficulty in this problem lies on depth estimation/assignment from a mono image, which actually does not have sufficient information. To estimate the depth map, we adopt a strategy of performing foreground/background separation first, then classifying a background depth profile by neural network, estimating foreground depth from image cues, and finally combining them. To enhance stereoscopic perception for the synthesized images viewed on 3D display, depth refinement based on bilateral filter and HVS-based contrast modification between the foreground and background are adopted. Subjective experiments show that the stereo images generated by using the proposed scheme can provide good 3D perception.