Vector quantization and signal compression
Vector quantization and signal compression
Surface reconstruction from unorganized points
SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques
Arithmetic coding for data compression
Communications of the ACM
BIRCH: an efficient data clustering method for very large databases
SIGMOD '96 Proceedings of the 1996 ACM SIGMOD international conference on Management of data
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Rendering from compressed textures
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
CURE: an efficient clustering algorithm for large databases
SIGMOD '98 Proceedings of the 1998 ACM SIGMOD international conference on Management of data
Accelerating exact k-means algorithms with geometric reasoning
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
QSplat: a multiresolution point rendering system for large meshes
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Spectral processing of point-sampled geometry
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Efficient high quality rendering of point sampled geometry
EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
An Efficient k-Means Clustering Algorithm: Analysis and Implementation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ray Tracing Point Set Surfaces
SMI '03 Proceedings of the Shape Modeling International 2003
Efficient Biased Sampling for Approximate Clustering and Outlier Detection in Large Data Sets
IEEE Transactions on Knowledge and Data Engineering
High-Quality Point-Based Rendering on Modern GPUs
PG '03 Proceedings of the 11th Pacific Conference on Computer Graphics and Applications
Statistical geometry representation for efficient transmission and rendering
ACM Transactions on Graphics (TOG)
Compression Domain Volume Rendering
Proceedings of the 14th IEEE Visualization 2003 (VIS'03)
Clustering high-dimensional data using an efficient and effective data space reduction
Proceedings of the 14th ACM international conference on Information and knowledge management
Hardware Rendering of 3D Geometry with Elevation Maps
SMI '06 Proceedings of the IEEE International Conference on Shape Modeling and Applications 2006
A fast k-means implementation using coresets
Proceedings of the twenty-second annual symposium on Computational geometry
Patterns for parallel programming
Patterns for parallel programming
IBM Journal of Research and Development
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Progressive compression of point-sampled models
SPBG'04 Proceedings of the First Eurographics conference on Point-Based Graphics
Compression of point-based 3D models by shape-adaptive wavelet coding of multi-height fields
SPBG'04 Proceedings of the First Eurographics conference on Point-Based Graphics
DUODECIM: a structure for point scan compression and rendering
SPBG'05 Proceedings of the Second Eurographics / IEEE VGTC conference on Point-Based Graphics
Octree-based progressive geometry coding of point clouds
SPBG'06 Proceedings of the 3rd Eurographics / IEEE VGTC conference on Point-Based Graphics
Octree-based point-cloud compression
SPBG'06 Proceedings of the 3rd Eurographics / IEEE VGTC conference on Point-Based Graphics
Hi-index | 0.00 |
We present a point-cloud compression algorithm that allows fast parallel decompression on the GPU suitable for interactive applications. The algorithm is based on vector quantization of an atlas of height-fields that have been sampled over primitive shapes which approximate the geometry. We introduce novel vector quantization acceleration techniques to facilitate fast compression as well. We achieve bitrates of less than four bits per normal-equipped point. Our method enables hole-free 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. Even lower bitrates are obtained for storage on disk if arithmetic coding is used.