# Learning 3D Shape Completion under Weak Supervision

arXiv: https://arxiv.org/abs/1805.07290 · HTML: https://mlsanity.com/paper/1805.07290/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2018.

## Built on by (most cited first, 30 of 40)

- [DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image](https://mlsanity.com/paper/2311.18610/) (2023)
- [Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation](https://mlsanity.com/paper/2312.07063/) (2023)
- [Point-Cloud Completion with Pretrained Text-to-image Diffusion Models](https://mlsanity.com/paper/2306.10533/) (2023)
- [Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations](https://mlsanity.com/paper/2107.10296/) (2021)
- [Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation](https://mlsanity.com/paper/2204.08196/) (2022)
- [PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories](https://mlsanity.com/paper/2206.04916/) (2022)
- [Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild](https://mlsanity.com/paper/2101.06860/) (2021)
- [Denoise and Contrast for Category Agnostic Shape Completion](https://mlsanity.com/paper/2103.16671/) (2021)
- [3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces](https://mlsanity.com/paper/2108.08653/) (2021)
- [Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments](https://mlsanity.com/paper/2312.09138/) (2023)
- [Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation](https://mlsanity.com/paper/2502.14247/) (2025)
- [Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction](https://mlsanity.com/paper/2109.04398/) (2021)
- [Learning Physically Realizable Skills for Online Packing of General 3D Shapes](https://mlsanity.com/paper/2212.02094/) (2022)
- [Pushing the Limits of 3D Shape Generation at Scale](https://mlsanity.com/paper/2306.11510/) (2023)
- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations](https://mlsanity.com/paper/2210.02045/) (2022)
- [Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability](https://mlsanity.com/paper/2402.12225/) (2024)
- [HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition](https://mlsanity.com/paper/2411.14628/) (2024)
- [DeepMend: Learning Occupancy Functions to Represent Shape for Repair](https://mlsanity.com/paper/2210.05728/) (2022)
- [3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions](https://mlsanity.com/paper/2311.16524/) (2023)
- [Multimodal Shape Completion via IMLE](https://mlsanity.com/paper/2106.16237/) (2021)
- [Vitruvio: 3D Building Meshes via Single Perspective Sketches](https://mlsanity.com/paper/2210.13634/) (2022)
- [DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair](https://mlsanity.com/paper/2211.12400/) (2022)
- [Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand](https://mlsanity.com/paper/2310.20350/) (2023)
- [High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling](https://mlsanity.com/paper/2112.11271/) (2021)
- [SPAC-Net: Rethinking Point Cloud Completion with Structural Prior](https://mlsanity.com/paper/2411.15066/) (2024)
- [Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding](https://mlsanity.com/paper/2504.13580/) (2025)
- [Virtually increasing the measurement frequency of LIDAR sensor utilizing a single RGB camera](https://mlsanity.com/paper/2302.05192/) (2023)
- [Sketch2Stress: Sketching with Structural Stress Awareness](https://mlsanity.com/paper/2306.05911/) (2023)
- [SSL-NBV: A Self-Supervised-Learning-Based Next-Best-View algorithm for Efficient 3D Plant Reconstruction by a Robot](https://mlsanity.com/paper/2410.14790/) (2024)

## Abstract (arXiv)

We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations; Learning-based approaches, in contrast, avoid the expensive optimization step by learning to directly predict complete shapes from incomplete observations in a fully-supervised setting. However, full supervision is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, i.e., learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. On synthetic benchmarks based on ShapeNet and ModelNet as well as on real robotics data from KITTI and Kinect, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with recent fully supervised baselines and outperforms data-driven approaches, while requiring less supervision and being significantly faster.