English

3D Photography using Context-aware Layered Depth Inpainting

Computer Vision and Pattern Recognition 2020-06-11 v3 Image and Video Processing

Abstract

We propose a method for converting a single RGB-D input image into a 3D photo - 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 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 fewer artifacts compared with the state of the arts.

Keywords

Cite

@article{arxiv.2004.04727,
  title  = {3D Photography using Context-aware Layered Depth Inpainting},
  author = {Meng-Li Shih and Shih-Yang Su and Johannes Kopf and Jia-Bin Huang},
  journal= {arXiv preprint arXiv:2004.04727},
  year   = {2020}
}

Comments

CVPR 2020. Project page: https://shihmengli.github.io/3D-Photo-Inpainting/ Code: https://github.com/vt-vl-lab/3d-photo-inpainting Demo: https://colab.research.google.com/drive/1706ToQrkIZshRSJSHvZ1RuCiM__YX3Bz

R2 v1 2026-06-23T14:46:03.257Z