Journal
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
Volume 29, Issue 11, Pages 4644-4654Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2023.3320220
Keywords
Rendering (computer graphics); Three-dimensional displays; Head; Photography; Image color analysis; Virtual reality; Cameras; Multi-layer images; inpainting; virtual reality; image-based rendering
Categories
Ask authors/readers for more resources
Multi-layer images are widely used for viewing natural scenes in virtual reality, but removing obstructive objects or editing the content is challenging. Researchers propose a multi-layer inpainting approach that addresses this issue in two stages.
Multi-layer images are currently the most prominent scene representation for viewing natural scenes under full-motion parallax in virtual reality. Layers ordered in diopter space contain color and transparency so that a complete image is formed when the layers are composited in a view-dependent manner. Once baked, the same limitations apply to multi-layer images as to conventional single-layer photography, making it challenging to remove obstructive objects or otherwise edit the content. Object removal before baking can benefit from filling disoccluded layers with pixels from background layers. However, if no such background pixels have been observed, an inpainting algorithm must fill the empty spots with fitting synthetic content. We present and study a multi-layer inpainting approach that addresses this problem in two stages: First, a volumetric area of interest specified by the user is classified with respect to whether the background pixels have been observed or not. Second, the unobserved pixels are filled with multi-layer inpainting. We report on experiments using multiple variants of multi-layer inpainting and compare our solution to conventional inpainting methods that consider each layer individually.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available