Z2P: Instant Visualization of Point Clouds

Metzer, Gal; Hanocka, Rana; Giryes, Raja; Mitra, Niloy J.; Cohen-Or, Daniel

Z2P: Instant Visualization of Point Clouds

Files

v41i2pp461-471.pdf (4.39 MB)

paper1034_2.mp4 (53.73 MB)

paper1034_3.pdf (11.61 MB)

Date

2022

Authors

Metzer, Gal
Hanocka, Rana
Giryes, Raja
Mitra, Niloy J.
Cohen-Or, Daniel

Publisher

The Eurographics Association and John Wiley & Sons Ltd.

Abstract

We present a technique for visualizing point clouds using a neural network. Our technique allows for an instant preview of any point cloud, and bypasses the notoriously difficult surface reconstruction problem or the need to estimate oriented normals for splat-based rendering. We cast the preview problem as a conditional image-to-image translation task, and design a neural network that translates point depth-map directly into an image, where the point cloud is visualized as though a surface was reconstructed from it. Furthermore, the resulting appearance of the visualized point cloud can be, optionally, conditioned on simple control variables (e.g., color and light). We demonstrate that our technique instantly produces plausible images, and can, on-the-fly effectively handle noise, non-uniform sampling, and thin surfaces sheets.

        @article{10.1111:cgf.14487
,
journal = {Computer Graphics Forum},
title = {{Z2P: Instant Visualization of Point Clouds
}},
author = {Metzer, Gal and 
Hanocka, Rana and 
Giryes, Raja and 
Mitra, Niloy J. and 
Cohen-Or, Daniel
},
year = {2022
},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.
},
ISSN = {1467-8659
},
DOI = {10.1111/cgf.14487
}
}