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

arXiv: https://arxiv.org/abs/2101.04493 · HTML: https://mlsanity.com/paper/2101.04493/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 17 of 17)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [3D Point Capsule Networks](https://mlsanity.com/paper/1812.10775/) (2018)
- [Point Cloud GAN](https://mlsanity.com/paper/1810.05795/) (2018)
- [FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation](https://mlsanity.com/paper/1712.07262/) (2017)
- [A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization](https://mlsanity.com/paper/1906.11478/) (2019)
- [Learning Embedding of 3D models with Quadric Loss](https://mlsanity.com/paper/1907.10250/) (2019)

## Built on by (most cited first, 20 of 20)

- [CAD-Recode: Reverse Engineering CAD Code from Point Clouds](https://mlsanity.com/paper/2412.14042/) (2024)
- [CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention](https://mlsanity.com/paper/2402.17678/) (2024)
- [CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations](https://mlsanity.com/paper/2208.10555/) (2022)
- [Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts](https://mlsanity.com/paper/2409.17106/) (2024)
- [SHARP Challenge 2023: Solving CAD History and pArameters Recovery from Point clouds and 3D scans. Overview, Datasets, Metrics, and Baselines](https://mlsanity.com/paper/2308.15966/) (2023)
- [SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes](https://mlsanity.com/paper/2304.06531/) (2023)
- [CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation](https://mlsanity.com/paper/2605.10873/) (2026)
- [CAD-Coder:Text-Guided CAD Files Code Generation](https://mlsanity.com/paper/2505.08686/) (2025)
- [CADReasoner: Iterative Program Editing for CAD Reverse Engineering](https://mlsanity.com/paper/2603.29847/) (2026)
- [MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans](https://mlsanity.com/paper/2510.23429/) (2025)
- [CADFS: A Big CAD Program Dataset and Framework for Computer-Aided Design with Large Language Models](https://mlsanity.com/paper/2605.01925/) (2026)
- [BRep Boundary and Junction Detection for CAD Reverse Engineering](https://mlsanity.com/paper/2409.14087/) (2024)
- [ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers](https://mlsanity.com/paper/2306.10798/) (2023)
- [Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds](https://mlsanity.com/paper/2107.13152/) (2021)
- [SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Design](https://mlsanity.com/paper/2603.13098/) (2026)
- [Automated Reconstruction of 3D Open Surfaces from Sparse Point Clouds](https://mlsanity.com/paper/2210.15059/) (2022)
- [Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning](https://mlsanity.com/paper/2104.14834/) (2021)
- [IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction](https://mlsanity.com/paper/2311.02552/) (2023)
- [A2Z-10M+: Geometric Deep Learning with A-to-Z BRep Annotations for AI-Assisted CAD Modeling and Reverse Engineering](https://mlsanity.com/paper/2603.12605/) (2026)
- [Agent-Aided Design for Dynamic CAD Models](https://mlsanity.com/paper/2604.15184/) (2026)

## 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.