A DIBR method based on inverse mapping and depth-aided image inpainting

Cheng, Cong; Liu, Ju; Yuan, Hui; Yang, Xiaohui; Liu, Wei

doi:10.1109/chinasip.2013.6625394

Cited by 5 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…α is 1 for a nonhole region and 0 for the hole pixels in I A depending on the selected viewpoint. Based on (21), most regions of the blended view are from the main virtual view, and some holes in the blended view are filled from the auxiliary virtual view.…”

Section: Adaptive Blending Of Virtual Viewsmentioning

confidence: 99%

Fast Hole Filling for View Synthesis in Free Viewpoint Video

Huang

ShaoYu

2020

Electronics

View full text Add to dashboard Cite

The recent emergence of three-dimensional (3D) movies and 3D television (TV) indicates an increasing interest in 3D content. Stereoscopic displays have enabled visual experiences to be enhanced, allowing the world to be viewed in 3D. Virtual view synthesis is the key technology to present 3D content, and depth image-based rendering (DIBR) is a classic virtual view synthesis method. With a texture image and its corresponding depth map, a virtual view can be generated using the DIBR technique. The depth and camera parameters are used to project the entire pixel in the image to the 3D world coordinate system. The results in the world coordinates are then reprojected into the virtual view, based on 3D warping. However, these projections will result in cracks (holes). Hence, we herein propose a new method of DIBR for free viewpoint videos to solve the hole problem due to these projection processes. First, the depth map is preprocessed to reduce the number of holes, which does not produce large-scale geometric distortions; subsequently, improved 3D warping projection is performed collectively to create the virtual view. A median filter is used to filter the hole regions in the virtual view, followed by 3D inverse warping blending to remove the holes. Next, brightness adjustment and adaptive image blending are performed. Finally, the synthesized virtual view is obtained using the inpainting method. Experimental results verify that our proposed method can produce a pleasant visibility of the synthetized virtual view, maintain a high peak signal-to-noise ratio (PSNR) value, and efficiently decrease execution time compared with state-of-the-art methods.

show abstract

Section: Adaptive Blending Of Virtual Viewsmentioning

confidence: 99%

Fast Hole Filling for View Synthesis in Free Viewpoint Video

Huang

ShaoYu

2020

Electronics

View full text Add to dashboard Cite

show abstract

“…In all simulations, we treat left viewpoint as the reference image and right viewpoint as the assistant image. The compared experimental results of our proposed method, the VSRS [24] virtual view synthesis of the method proposed in [25] and image inpainting with [20] are shown in Fig. 7 and Fig.…”

Section: Experiments and Analysis A Evaluation Of Video Sequence Using Our Algorithmmentioning

confidence: 99%

“…This is because the methods of VSRS [24] and Criminisi et al [20] do not take the depth information into consideration. Besides, all of the three methods of [24], [25] and [20] simply take the newly inpatinted pixels have the same confidence term, which leads the holes filled with wrong pixels. Furthermore, there are artifacts at the edge of foreground objects, which can be found in A3 of Fig.…”

Section: Experiments and Analysis A Evaluation Of Video Sequence Using Our Algorithmmentioning

confidence: 99%

“…7(c). This is because the algorithm proposed in [25] simply warped the pixels with inverse 3D warping function and fill the warped holes without eliminating the pixels where may occur artifacts. Virtual view generated by our proposed method is shown in Fig.…”

Section: Experiments and Analysis A Evaluation Of Video Sequence Using Our Algorithmmentioning

confidence: 99%

“…This is because our proposed algorithm only warping one image and disocclusion region instead of warping the two whole images. Method [25] has the highest complexity because it uses inverse 3D warping to warp the two images which costs more time. Compared with Criminisi's method [20], our proposed method costs a little more time.…”

Section: Experiments and Analysis A Evaluation Of Video Sequence Using Our Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

An Improved Depth Image Based Virtual View Synthesis Method for Interactive 3D Video

Zhu

Yan

2019

IEEE Access

View full text Add to dashboard Cite

Depth image-based rendering (DIBR) is one of the main techniques in interactive 3D video systems. But a critical problem of DIBR is that how to eliminate the holes appearing in virtual view images. In this paper, an improved depth image based virtual view synthesis algorithm is proposed. In depth map pre-processing, only local areas of the depth map with sudden changes are pre-processed by the asymmetric filter. After this, we combine the forward and inverse 3D-warping to synthesize the virtual view. Firstly, it warps the left image to the virtual view and then only reversely warps the region of the holes in the virtual view to the right view to get the lost information of holes. Compared with the traditional method which have to warp the two whole images, computation cost can be reduced by 30% efficiently. Finally, we employ an improved image inpainting based on depth information to fill hole regions. We have improved the method in two portions: 1) depth information is added to the priority computation and searching the best matching patch and 2) as the filling proceeds, the confidence term of the newly inpainted pixels is updated with the mean square error (MSE) of pixels in the target matching patch and the source matching patch. Experimental results show significant objective and subjective gains of the proposed method in comparison to the reference methods.INDEX TERMS DIBR, 3D warping, hole filling, depth map.

show abstract