Abstract
The depth image based rendering (DIBR) is a popular technology for 3D video and free viewpoint video (FVV) synthesis, by which numerous virtual views can be generated from a single reference view and its depth image. However, some artifacts are produced in the DIBR process and reduce the visual quality of virtual view. Due to the diversity of artifacts, effectively handling them becomes a challenging task. In this paper, an artifact handling method based on depth image is proposed. The reference image and its depth image are extended to fill the holes that belong to the out-of-field regions. A depth image preprocessing method is applied to project the ghosts to their correct place. The 3D warping process is optimized by an adaptive one-to-four method to deal with the cracks and pixel overlapping. For disocclusions, we calculate depth and background terms of the filling priority based on depth information. The search for the best matching patch is performed simultaneously in the reference image and the virtual image. Moreover, adaptive patch size is used in all hole-filling processes. Experimental results demonstrate the effectiveness of the proposed method, which has better performance compared with previous methods in subjective and objective evaluation.
Highlights
With the development of computer technology, 3D video has become increasingly popular recently.It provides users with a more authentic and interactive viewing experience [1]
The decrement of the depth value from the foreground to the background causes the disocclusion to be divided into several small holes, which are filled by the image inpainting
In order to evaluate the performance of the proposed method, the multi-view video plus depth sequences “Ballet” and “Breakdancers” provided by Microsoft Research are used in our experiment [30]
Summary
With the development of computer technology, 3D video has become increasingly popular recently. One practical way is to create virtual views on the receiving end In this context, depth image based rendering (DIBR) is a better choice [4]. All pixels in the reference image are re-projected into the world are re-projected into the world coordinate system according to the depth information. One is the overlap of pixels, which will affect the occlusion relationship occlusion relationship between objects in the virtual image if not processed. A virtual image is generated by the novel view synthesis method based on the DIBR process. TheThe hole pixels atatthe andinversely inverselyprojected projected into reference to calculate the extended region of reference the reference image its depth image. The 3D warping process is modified to avoid cracks and pixel overlapping.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
