Tag: 3d

Making Pictures 3D using Context-aware Layered Depth Inpainting

Making Pictures 3D using Context-aware Layered Depth Inpainting

Several Chinese Ph.D. students wrote a PyTorch program that can turn your holiday pictures into 3D sceneries. They call it 3D photo inpainting. Here are some examples

And here’s the new method compares to previous techniques:

Here are several links to more detailed resources: [Paper] [Project Website] [Google Colab] [GitHub]

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 fewer artifacts when compared with the state-of-the-arts.

Via github.com/vt-vl-lab/3d-photo-inpainting
3D Photography Inpainting: Exploring Art with AI. - Towards Data ...
I loved this one as well, but it could be a different technique used, via Medium
Generating 3D Faces from 2D Photographs

Generating 3D Faces from 2D Photographs

Aaron Jackson, Adrian Bulat, Vasileios Argyriou and Georgios Tzimiropoulos
of the Computer Vision Laboratory of the University of Nottingham built a neural network that generates a full 3D image of a single portrait photograph. They turn a photograph like this…

PVDL corporate

… into an accurately creepy 3D image like this.

faceimage

You can try it with your own or other photographs here. I found that images with white background get the best results. On their project website you can read more about the underlying convolutional neural network.

Update 21-10-2017: One of my favorite YouTube channels explains how the models were trained and the data used: