
TL;DR
This paper introduces a novel surfel-based rendering technique that efficiently approximates complex 3D scenes with billions of triangles in real time, using precomputed, surface-only points for high-quality visualization.
Contribution
It presents a new method for generating and utilizing surfels to render highly complex scenes efficiently in real time, with surfels precomputed to ensure visibility and good visual approximation.
Findings
Capable of rendering scenes with billions of triangles in real time.
Provides high image quality with complex, polygonal 3D scenes.
Uses precomputed surfels that are surface-only, well-distributed, and sorted for efficient rendering.
Abstract
In this paper we describe a new technique to generate and use surfels for rendering of highly complex, polygonal 3D scenes in real time. The basic idea is to approximate complex parts of the scene by rendering a set of points (surfels). The points are computed in a preprocessing step and offer two important properties: They are placed only on the visible surface of the scene's geometry and they are distributed and sorted in such a way, that every prefix of points is a good visual representation of the approximated part of the scene. An early evaluation of the method shows that it is capable of rendering scenes consisting of several billions of triangles with high image quality.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Computer Graphics and Visualization Techniques · 3D Shape Modeling and Analysis
