mlsanityData to 7 Oct 2026

Multimodal Shape Completion via IMLE

arXiv 2106.16237 ↗First posted 30 Jun 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Shape completion is the problem of completing partial input shapes such as partial scans. This problem finds important applications in computer vision and robotics due to issues such as occlusion or sparsity in real-world data. However, most of the existing research related to shape completion has been focused on completing shapes by learning a one-to-one mapping which limits the diversity and creativity of the produced results. We propose a novel multimodal shape completion technique that is effectively able to learn a one-to-many mapping and generates diverse complete shapes. Our approach is based on the conditional Implicit MaximumLikelihood Estimation (IMLE) technique wherein we condition our inputs on partial 3D point clouds. We extensively evaluate our approach by comparing it to various baselines both quantitatively and qualitatively. We show that our method is superior to alternatives in terms of completeness and diversity of shapes.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 30 Jun 2021.

Builds on

29 of 44 references.

References · 29

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  6. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  7. 2018PCN: Point Completion Networkcited by 382
  8. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  9. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  10. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  11. 2016Learning in Implicit Generative Modelscited by 124
  12. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
17 more
  1. 2020Cascaded Refinement Network for Point Cloud Completioncited by 112
  2. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  3. 2021Variational Relational Point Completion Networkcited by 103
  4. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  5. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  6. 2020PIE-NET: Parametric Inference of Point Cloud Edgescited by 67
  7. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  8. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  9. 2018Diverse Image Synthesis from Semantic Layouts via Conditional IMLEcited by 60
  10. 2018Learning 3D Shape Completion under Weak Supervisioncited by 40
  11. 2021ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completioncited by 28
  12. 2017Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networkscited by 23
  13. 2021Learning to Generate 3D Shapes with Generative Cellular Automatacited by 22
  14. 2020Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimationcited by 13
  15. 2020RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifierscited by 10
  16. 2019LOGAN: Unpaired Shape Transform in Latent Overcomplete Spacecited by 8
  17. 2020Generating Unobserved Alternativescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  2. 20233D VR Sketch Guided 3D Shape Prototyping and Explorationcited by 12
  3. 2024Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automatacited by 2
  4. 2025Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruptioncited by 0
  5. 2026ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modellingcited by 0