Z2P: Instant Visualization of Point Clouds
This provides a faster, more robust visualization method for 3D data processing, though it is incremental as it builds on existing neural translation techniques.
The paper tackles the problem of visualizing point clouds without surface reconstruction or oriented normals by using a neural network for conditional image-to-image translation, resulting in instant, plausible previews that handle noise and non-uniform sampling effectively.
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.