mlsanityData to 7 Oct 2026

PvDeConv: Point-Voxel Deconvolution for Autoencoding CAD Construction in 3D

arXiv 2101.04493 ↗First posted 12 Jan 2021cs.CV cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

We propose a Point-Voxel DeConvolution (PVDeConv) module for 3D data autoencoder. To demonstrate its efficiency we learn to synthesize high-resolution point clouds of 10k points that densely describe the underlying geometry of Computer Aided Design (CAD) models. Scanning artifacts, such as protrusions, missing parts, smoothed edges and holes, inevitably appear in real 3D scans of fabricated CAD objects. Learning the original CAD model construction from a 3D scan requires a ground truth to be available together with the corresponding 3D scan of an object. To solve the gap, we introduce a new dedicated dataset, the CC3D, containing 50k+ pairs of CAD models and their corresponding 3D meshes. This dataset is used to learn a convolutional autoencoder for point clouds sampled from the pairs of 3D scans - CAD models. The challenges of this new dataset are demonstrated in comparison with other generative point cloud sampling models trained on ShapeNet. The CC3D autoencoder is efficient with respect to memory consumption and training time as compared to stateof-the-art models for 3D data generation.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 17 of its 25 references that are in the map. First posted on arXiv 12 Jan 2021.

Builds on

17 of 25 references.

References · 17

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  8. 2018PCN: Point Completion Networkcited by 382
  9. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  10. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  11. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  12. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
5 more
  1. 20183D Point Capsule Networkscited by 106
  2. 2018Point Cloud GANcited by 79
  3. 2017FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformationcited by 24
  4. 2019A Convolutional Decoder for Point Clouds using Adaptive Instance Normalizationcited by 8
  5. 2019Learning Embedding of 3D models with Quadric Losscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 4; 2025: 2; 2026: 6.

20 papers.

Sort:

By area:

  1. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 63
  2. 2024CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attentioncited by 62
  3. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 30
  4. 2024Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Promptscited by 22
  5. 2023SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselinescited by 19
  6. 2023SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapescited by 13
  7. 2025CAD-Coder:Text-Guided CAD Files Code Generationcited by 8
  8. 2026CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generationcited by 7
  9. 2024BRep Boundary and Junction Detection for CAD Reverse Engineeringcited by 4
  10. 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scanscited by 4
  11. 2026CADReasoner: Iterative Program Editing for CAD Reverse Engineeringcited by 4
  12. 2026CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Modelscited by 4
8 more
  1. 2023ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformerscited by 3
  2. 2021Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Cloudscited by 2
  3. 2026SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Designcited by 2
  4. 2022Automated Reconstruction of 3D Open Surfaces from Sparse Point Cloudscited by 1
  5. 2021Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learningcited by 0
  6. 2023IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstructioncited by 0
  7. 2026A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineeringcited by 0
  8. 2026Agent-Aided Design for Dynamic CAD Modelscited by 0