ML Anthology

3D Photography Using Context-Aware Layered Depth Inpainting

Meng-Li Shih, Shih-Yang Su, Johannes Kopf, Jia-Bin Huang
CVPR 2020
doi:10.1109/CVPR42600.2020.00805 /cvpr/2020/shih2020cvpr-3d/

Abstract

We propose a method for converting a single RGB-D input image into a 3D photo, i.e., a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view. We use a Layered Depth Image with explicit pixel connectivity as underlying representation, and present a learning-based inpainting model that iteratively synthesizes new local color-and-depth content into the occluded region in a spatial context-aware manner. The resulting 3D photos can be efficiently rendered with motion parallax using standard graphics engines. We validate the effectiveness of our method on a wide range of challenging everyday scenes and show less artifacts when compared with the state-of-the-arts.

PDF CVPR Semantic Scholar

Cite

Text

Shih et al. "3D Photography Using Context-Aware Layered Depth Inpainting." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00805

Markdown

[Shih et al. "3D Photography Using Context-Aware Layered Depth Inpainting." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/shih2020cvpr-3d/) doi:10.1109/CVPR42600.2020.00805

BibTeX

@inproceedings{shih2020cvpr-3d,
  title     = {{3D Photography Using Context-Aware Layered Depth Inpainting}},
  author    = {Shih, Meng-Li and Su, Shih-Yang and Kopf, Johannes and Huang, Jia-Bin},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00805},
  url       = {https://mlanthology.org/cvpr/2020/shih2020cvpr-3d/}
}