Skip to content

Table of contents

Contents

Nineteen chapters across five parts. 4 are free to read in full. The rest open their first section as a preview.

19 chapters5 h 54 min4 free
Part I

Foundations

4 ch · 79 min
  1. 01Introduction to 3D Point CloudsFreeWhat a point cloud is, where it comes from, and the pipeline this book follows.15m
  2. 02LiDAR PrinciplesFreeThe physics of laser ranging, from the pulse outward to the georeferenced point.22m
  3. 03Acquisition SystemsFreeAirborne, terrestrial, mobile, UAV, handheld: how to choose, and what each one quietly fails at.26m
  4. 04Data Formats and Spatial IndexingLAS, LAZ, E57, COPC, and the kd-tree / octree machinery underneath them.16m
Part II

Preprocessing

4 ch · 67 min
  1. 05Sampling and ResamplingVoxel-grid, farthest-point, Poisson-disk: when each one is the right answer.14m
  2. 06Filtering and DenoisingStatistical, radius, and learned outlier removal, evaluated on real scans.15m
  3. 07Normal Estimation and CurvaturePCA-based normal estimation, orientation, and what curvature actually measures.16m
  4. 08RegistrationPairwise and global alignment: ICP and its modern variants, plus learned matchers.22m
Part III

Core Processing

5 ch · 87 min
  1. 09Ground ExtractionCloth simulation, progressive TIN, and how each fails under dense vegetation.18m
  2. 10Local Features and KeypointsDetecting repeatable points across scans before describing them.14m
  3. 11Segmentation and ClusteringRANSAC, region growing, DBSCAN, and the geometry of separating one object from the next.19m
  4. 12ClassificationFrom hand-tuned rules to random forests to PointNet, with honest accuracy numbers.20m
  5. 13Feature DescriptorsSHOT, FPFH, and learned descriptors as the front door to registration and classification.16m
Part IV

Advanced Processing

3 ch · 51 min
  1. 14Change DetectionCloud-to-cloud, cloud-to-mesh, and the M3C2 algorithm for terrain monitoring.17m
  2. 15Surface ReconstructionPoisson, alpha shapes, ball-pivoting, and modern implicit reconstructions.18m
  3. 16Object ReconstructionFrom segmented points to BIM-ready geometry, with a focus on buildings.16m
Part V

Frontiers

3 ch · 70 min
  1. 17ApplicationsFreeWhere the algorithms go to work: mapping, infrastructure, heritage, autonomous systems.28m
  2. 18Deep Learning on Point CloudsPointNet to PointNeXt and the architectures that actually generalise across datasets.22m
  3. 19Neural Rendering and Gaussian SplattingNeRF, 3DGS, and the new boundary between point clouds and view synthesis.20m

Want the complete book?

One email when it ships. Nothing else.