Z2P: Instant Visualization of Point Clouds

G. Metzer, R. Hanocka, R. Giryes, N. J. Mitra, D. Cohen-Or

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


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.

Original languageEnglish
Pages (from-to)461-471
Number of pages11
JournalComputer Graphics Forum
Issue number2
StatePublished - May 2022


Dive into the research topics of 'Z2P: Instant Visualization of Point Clouds'. Together they form a unique fingerprint.

Cite this