mlsanityData to 7 Oct 2026

CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds

arXiv 2109.00113 ↗First posted 31 Aug 2021cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Representing human-made objects as a collection of base primitives has a long history in computer vision and reverse engineering. In the case of high-resolution point cloud scans, the challenge is to be able to detect both large primitives as well as those explaining the detailed parts. While the classical RANSAC approach requires case-specific parameter tuning, state-of-the-art networks are limited by memory consumption of their backbone modules such as PointNet++, and hence fail to detect the fine-scale primitives. We present Cascaded Primitive Fitting Networks (CPFN) that relies on an adaptive patch sampling network to assemble detection results of global and local primitive detection networks. As a key enabler, we present a merging formulation that dynamically aggregates the primitives across global and local scales. Our evaluation demonstrates that CPFN improves the state-of-the-art SPFN performance by 13-14% on high-resolution point cloud datasets and specifically improves the detection of fine-scale primitives by 20-22%.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

26 of 41 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  7. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  8. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  9. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  10. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  11. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  12. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
14 more
  1. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  2. 2019CvxNet: Learnable Convex Decompositioncited by 173
  3. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  4. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  5. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  6. 2020ParSeNet: A Parametric Surface Fitting Network for 3D Point Cloudscited by 96
  7. 2018Supervised Fitting of Geometric Primitives to 3D Point Cloudscited by 90
  8. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  9. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 77
  10. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  11. 2019Deep Parametric Shape Predictions using Distance Fieldscited by 30
  12. 2020Learning Generative Models of Shape Handlescited by 25
  13. 2020Modeling 3D Shapes by Reinforcement Learningcited by 20
  14. 2019Large-scale 3D point cloud representations via graph inception networks with applications to autonomous drivingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 8; 2024: 5; 2025: 3; 2026: 5.

24 papers.

Sort:

By area:

  1. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  2. 2021Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinderscited by 59
  3. 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
  4. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
  5. 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
  6. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  7. 2024Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorizationcited by 34
  8. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  9. 2025PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformercited by 12
  10. 2023PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Cloudscited by 10
  11. 2021HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulationcited by 5
  12. 2025Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Predictioncited by 4
12 more
  1. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  2. 2023A Survey of Methods for Converting Unstructured Data to CSG Modelscited by 3
  3. 2024Robust Shape Fitting for 3D Scene Abstractioncited by 3
  4. 2024MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Imagescited by 3
  5. 2023QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Cloudscited by 2
  6. 20233D detection of roof sections from a single satellite image and application to LOD2-building reconstructioncited by 1
  7. 2025Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformerscited by 1
  8. 2026BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularitycited by 1
  9. 2026Unified Primitive Proxies for Structured Shape Completioncited by 0
  10. 2026BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splattingcited by 0
  11. 2026A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineeringcited by 0
  12. 2026GeoFusion-CAD: Structure-Aware Diffusion with Geometric State Space for Parametric 3D Designcited by 0