A Parallelly Decodeable Compression Scheme for Efficient Point-Cloud Rendering

Abstract

We present a point-cloud compression algorithm that allows fast parallel decompression on the GPU for interactive applications. We achieve bitrates of less than four bits per normal-equipped point. Our method enables holefree level-of-detail point rendering. We also show that using only up to two bits per point, high-quality renderings can still be obtained if normals are estimated in image-space. The algorithm is based on vector quantization of an atlas of height-fields that have been sampled over primitive shapes which approximate the geometry.