2D-to-3D stereoscopic conversion: depth-map estimation in a 2D single-view image

Ko, Jaeseung; Kim, Manbae; Kim, Changick

doi:10.1117/12.736131

Cited by 31 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the technology of converting 2D video into 3D video, the rendering of depth image is very critical and important. In this paper, we get the depth map by using the focus information of monocular 2D image [2]. This method is represented as the flow chart shown in Fig.…”

Section: Proposed Methodsmentioning

confidence: 99%

A Novel High-Order Statistics Map Based Method for Depth Map Generation of Static Scene

Guan

Shen

et al. 2013

2013 Seventh International Conference on Image and Graphics

View full text Add to dashboard Cite

Considering the increasing need of the contents of 3D video, it is significant to do some research in 2D-to-3D conversion. The depth map is necessary for this processing. In this paper, we propose an effective method to estimate the depth information of the low depth field images of static scenes. Firstly, construct a high-order statistics (HOS) map, which represents the high-frequency components of the input image. Then, conduct image segmentation to partition the image into different regions. Finally, assign the depth information to the regions and get a depth map.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

A Novel High-Order Statistics Map Based Method for Depth Map Generation of Static Scene

Guan

Shen

et al. 2013

2013 Seventh International Conference on Image and Graphics

View full text Add to dashboard Cite

show abstract

“…First of all, degree of focus of segmented regions is one of them [5]. To this end, an image is segmented to partition an image into homogeneous regions in terms of the degree of focus.…”

Section: Display For Raising Immersivenessmentioning

confidence: 99%

Personalized Display Techniques for Next Generation DTV

Kim¹,

Lee²,

Ko³

et al. 2008

2008 10th International Conference on Advanced Communication Technology

Self Cite

View full text Add to dashboard Cite

With the advent of the high resolution digital television (DTV), the demand for personalized display techniques has dramatically increased. In order to meet this demand, it is necessary to provide users with a personalized display environment. In this paper, we propose a novel framework to enhance users' viewing experience. To this end, we break the personalized displays into three categories: raising immersiveness, better understanding of contents, and viewing pleasure. This system can be applied to the next generation DTV, which envisages personalized display techniques. Extension of the proposed system is our on-going work to provide more various personalized viewing options.

show abstract

“…The technique concerning the conversion of 2D videos to stereoscopic ones is commonly called 2D/3D video conversion [5]- [9], [11]- [15]. Up to now, there are two kinds of 2D/3D video conversion schemes.…”

Section: Introductionmentioning

confidence: 99%

A 2D to 3D conversion scheme based on depth cues analysis for MPEG videos

Lin

Yeh

Chen

et al. 2010

2010 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

In this article, we propose a 2D to 3D video conversion scheme for MPEG videos. The difficulty for 2D/3D conversion problem lies on depth estimation/ assignment with insufficient information. Our depth assignment is based on the analyses of multiple cues, e.g., motion parallax, atmospheric perspective, texture gradient, linear perspective, and relative height, separately for the foreground objects and the background area. To fit more kinds of videos, the proposed depth assignment scheme is content-adaptive by segmenting a video into shots and classifying each of them into three categories for different conversion schemes. Subjective experiments show that the 3D stereo video generated by using our depth assignment scheme and the Depth Image Based Rendering (DIBR) technique presents little difference to that created based on the depth ground truths.

show abstract

2D-to-3D stereoscopic conversion: depth-map estimation in a 2D single-view image

Cited by 31 publications

References 8 publications

A Novel High-Order Statistics Map Based Method for Depth Map Generation of Static Scene

A Novel High-Order Statistics Map Based Method for Depth Map Generation of Static Scene

Personalized Display Techniques for Next Generation DTV

A 2D to 3D conversion scheme based on depth cues analysis for MPEG videos

Contact Info

Product

Resources

About