Dictionary based hole filling with assistance of depth

Abstract

Depth-image-based-rendering (DIBR) has received much attention in recent years as a promising technology for 3DTV systems. However, holes are inevitable in DIBR during the view synthesis procedure because the scene area, which has been occluded in the reference image, become visible in the synthesized virtual view. In this paper, we propose dictionary based hole filling with the assistance of depth. Because holes generally come from background area, we first segment background from foreground with the assistance of depth. Then, we construct a dictionary for hole filling from background. Finally, we employ the dictionary to fill holes in the synthesized virtual view. Experimental results demonstrate that the proposed method achieves good performance in hole filling in terms of visual quality and quantitative measures.

SECI-GAN: Semantic and Edge Completion for dynamic objects removal

“…Given an image with missing regions, image inpainting aims at synthesizing the missing content by producing a visually realistic and semantically coherent image. For this reason, it is also known in literature as image completion or image holefilling [34], [22], [21], [8]. The missing pixels are assigned the value 0 in a binary mask, the non-missing pixels are assigned the value 1.…”