An efficient approach for 2D to 3D video conversion based on structure from motion

Liu, Wei; Wu, Yihong; Guo, Fusheng; Hu, Zhanyi

doi:10.1007/s00371-013-0904-3

Cited by 11 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this part, another experiment is carried out to further verify the disocclusion reduction ability of the proposed filter at depth map preprocess step. A novel approach in our previous works [29], which needs more computational costs but can generate more precise depth maps, is adopted to test sets Flower and Castle for new reference depth maps. These new reference depth maps are regarded as depth map groundtruth in this experiment.…”

Section: Analysis Of Experimental Results and Depth Map Evaluationmentioning

confidence: 99%

A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework

Liu

Tang

Ding

et al. 2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

Depth image based rendering (DIBR), which is utilized to render virtual views with a color image and the corresponding depth map, is one of the key procedures in the 2D to 3D conversion process. However, some troubling problems, such as depth edge misalignment, disocclusion occurrences and cracks at resampling, still exist in current DIBR systems. To solve these problems, in this paper, we present a robust depth image based rendering scheme for stereoscopic view synthesis. The cores of the proposed scheme are two depth map filters which share a common domain transform based filtering framework. As a first step, a filter of this framework is carried out to realize texture-depth boundary alignments and directional disocclusion reduction smoothing simultaneously. Then after depth map 3D warping, another adaptive filter is used on the warped depth maps with delivered scene gradient structures to further diminish the remaining cracks and noises. Finally, with the optimized depth map of the virtual view, backward texture warping is adopted to retrieve the final texture virtual view. The proposed scheme enables to yield visually satisfactory results for high quality 2D to 3D conversion. Experimental results demonstrate the excellent performances of the proposed approach. key words: depth image-based rendering, domain transform, adaptive smoothing, stereoscopic image generation

show abstract

Section: Analysis Of Experimental Results and Depth Map Evaluationmentioning

confidence: 99%

A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework

Liu

Tang

Ding

et al. 2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to these reasons, a number of additional intermediate frames need to be generated. There are numerous ways of generating intermediate frames, such as basic interpolation between input images, flow-field interpolation [61], image-based rendering [2,6], and structure approximation [1,5,15,17,31,34,38,45,58,60] to create depth mesh.…”

Section: Scene Depth Approximationmentioning

confidence: 99%

Kinetic depth images: flexible generation of depth perception

2016

View full text Add to dashboard Cite

In this paper we present a systematic approach to create smoothly varying images from a pair of photographs to facilitate enhanced awareness of the depth structure of a given scene. Since our system does not rely on sophisticated display technologies such as stereoscopy or auto-stereoscopy for depth awareness, it (a) is inexpensive and widely accessible, (b) does not suffer from vergence -accommodation fatigue, and (c) works entirely with monocular depth cues. Our approach enhances the depth awareness by optimizing across a number of features such as depth perception, optical flow, saliency, centrality, and disocclusion artifacts. We report the results of user studies that examine the relationship between depth perception, relative velocity, spatial perspective effects, and the positioning of the pivot point and use them when generating kinetic-depth images. We also present a novel depth re-mapping method guided by perceptual relationships based on the results of our user study. We validate our system by presenting a user study that compares the output quality of our proposed method against other existing alternatives on a wide range of images.

show abstract

“…According to the relationship between the movements of the object and the camera, four cases are listed: 15 static camera, static scene (nonobject motion and noncamera motion); static camera, dynamic scene (object motion only); dynamic camera, static scene (camera motion only); and dynamic camera, dynamic scene (camera motion and object motion). Thus, the movements of the object and the camera must be considered for constructing depth from video sequences.…”

Section: Related Workmentioning

confidence: 99%

“…According to the relationship between the movements of the object and the camera, four cases are listed: 15 static camera, static scene (nonobject motion and noncamera motion); static camera, dynamic scene (object motion only); dynamic camera, static scene (camera motion only); and dynamic camera, dynamic scene (camera motion and object motion). 15 Lim and Park 5 proposed a new depth generation approach based on SFM techniques and used image-based rendering to generate the desired multiview video in a relatively short time. Research on the second case has appeared in many papers in the literature.…”

Section: Related Workmentioning

confidence: 99%

Comprehensive depth estimation algorithm for efficient stereoscopic content creation in three-dimensional video systems

Jiang

2015

Opt. Eng

View full text Add to dashboard Cite

Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspxAbstract. Two-dimensional to three-dimensional (3-D) conversion in 3-D video applications has attracted great attention as it can alleviate the problem of stereoscopic content shortage. Depth estimation is an essential part of this conversion since the depth accuracy directly affects the quality of a stereoscopic image. In order to generate a perceptually reasonable depth map, a comprehensive depth estimation algorithm that considers the scenario type is presented. Based on the human visual system mechanism, which is sensitive to a change in the scenario, this study classifies the type of scenario into four classes according to the relationship between the movements of the camera and the object, and then leverages different strategies on the basis of the scenario type. The proposed strategies efficiently extract the depth information from different scenarios. In addition, the depth generation method for a scenario in which there is no motion, neither of the object nor the camera, is also suitable for the single image. Qualitative and quantitative evaluation results demonstrate that the proposed depth estimation algorithm is very effective for generating stereoscopic content and providing a realistic visual experience. © 2015 Society of Photo-Optical Instrumentation Engineers (SPIE) Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073103-2 July 2015 • Vol. 54(7) Xu and Jiang: Comprehensive depth estimation algorithm for efficient stereoscopic content creation. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073103-3 July 2015 • Vol. 54(7) Xu and Jiang: Comprehensive depth estimation algorithm for efficient stereoscopic content creation. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073103-5 July 2015 • Vol. 54(7) Xu and Jiang: Comprehensive depth estimation algorithm for efficient stereoscopic content creation. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073103-10 July 2015 • Vol. 54(7) Xu and Jiang: Comprehensive depth estimation algorithm for efficient stereoscopic content creation. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073103-12 July 2015 • Vol. 54(7) Xu and Jiang: Comprehensive depth estimation algorithm for efficient stereoscopic content creation. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary...

show abstract

An efficient approach for 2D to 3D video conversion based on structure from motion

Cited by 11 publications

References 21 publications

A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework

A Robust Depth Image Based Rendering Scheme for Stereoscopic View Synthesis with Adaptive Domain Transform Based Filtering Framework

Kinetic depth images: flexible generation of depth perception

Comprehensive depth estimation algorithm for efficient stereoscopic content creation in three-dimensional video systems

Contact Info

Product

Resources

About