Disocclusion Handling Using Depth-Based Inpainting
2013 (English)In: Proceedings of MMEDIA 2013, The Fifth InternationalConferences on Advances in Multimedia, Venice, Italy, 2013, International Academy, Research and Industry Association (IARIA), 2013, 136-141 p.Conference paper, Abstract (Refereed)
Depth image based rendering (DIBR) plays an important role in producing virtual views using 3D-video formats such as video plus depth (V+D) and multi view-videoplus-depth (MVD). Pixel regions with non-defined values (due to disoccluded areas) are exposed when DIBR is used. In this paper, we propose a depth-based inpainting method aimed to handle Disocclusions in DIBR from V+D and MVD. Our proposed method adopts the curvature driven diffusion (CDD) model as a data term, to which we add a depth constraint. In addition, we add depth to further guide a directional priority term in the exemplar based texture synthesis. Finally, we add depth in the patch-matching step to prioritize background texture when inpainting. The proposed method is evaluated by comparing inpainted virtual views with corresponding views produced by three state-of-the-art inpainting methods as references. The evaluation shows the proposed method yielding an increased objective quality compared to the reference methods, and visual inspection further indicate an improved visual quality.
Place, publisher, year, edition, pages
International Academy, Research and Industry Association (IARIA), 2013. 136-141 p.
video plus depth, warping, depth-image-based rendering, inpainting
Signal Processing Other Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:miun:diva-18890ScopusID: 2-s2.0-84905842575Local ID: STCOAI: oai:DiVA.org:miun-18890DiVA: diva2:619541
Fifth International Conferences on Advances in Multimedia; MMEDIA 2013; Apr 21-26 2013; Venice, Italy