TY - JOUR
T1 - Z2P
T2 - Instant Visualization of Point Clouds
AU - Metzer, G.
AU - Hanocka, R.
AU - Giryes, R.
AU - Mitra, N. J.
AU - Cohen-Or, D.
N1 - Publisher Copyright: © 2022 The Author(s) Computer Graphics Forum © 2022 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
PY - 2022/5
Y1 - 2022/5
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85131016618&partnerID=8YFLogxK
U2 - https://doi.org/10.1111/cgf.14487
DO - https://doi.org/10.1111/cgf.14487
M3 - مقالة
SN - 0167-7055
VL - 41
SP - 461
EP - 471
JO - Computer Graphics Forum
JF - Computer Graphics Forum
IS - 2
ER -