mlsanityData to 14 Oct 2026

DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair

arXiv 2211.12400 ↗First posted 22 Nov 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce DeepJoin, an automated approach to generate high-resolution repairs for fractured shapes using deep neural networks. Existing approaches to perform automated shape repair operate exclusively on symmetric objects, require a complete proxy shape, or predict restoration shapes using low-resolution voxels which are too coarse for physical repair. We generate a high-resolution restoration shape by inferring a corresponding complete shape and a break surface from an input fractured shape. We present a novel implicit shape representation for fractured shape repair that combines the occupancy function, signed distance function, and normal field. We demonstrate repairs using our approach for synthetically fractured objects from ShapeNet, 3D scans from the Google Scanned Objects dataset, objects in the style of ancient Greek pottery from the QP Cultural Heritage dataset, and real fractured objects. We outperform three baseline approaches in terms of chamfer distance and normal consistency. Unlike existing approaches and restorations using subtraction, DeepJoin restorations do not exhibit surface artifacts and join closely to the fractured region of the fractured shape. Our code is available at: https://github.com/Terascale-All-sensing-Research-Studio/DeepJoin.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 53 of its 85 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

53 of 85 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2020Convolutional Occupancy Networkscited by 761
  8. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  9. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  10. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  11. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  12. 2018PCN: Point Completion Networkcited by 384
38 more
  1. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  2. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  3. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  4. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  5. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  6. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  7. 2019Morphing and Sampling Network for Dense Point Cloud Completioncited by 132
  8. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  9. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  10. 2017CSGNet: Neural Shape Parser for Constructive Solid Geometrycited by 106
  11. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  12. 2021Variational Relational Point Completion Networkcited by 104
  13. 2017ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scanscited by 103
  14. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  15. 2020Deep Implicit Templates for 3D Shape Representationcited by 86
  16. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  17. 2020PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representationscited by 81
  18. 2020UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Treecited by 78
  19. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  20. 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
  21. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  22. 2019Efficient Semantic Scene Completion Network with Spatial Group Convolutioncited by 66
  23. 2020Curriculum DeepSDFcited by 62
  24. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  25. 2016VConv-DAE: Deep Volumetric Shape Learning Without Object Labelscited by 50
  26. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  27. 2018Learning 3D Shape Completion under Weak Supervisioncited by 40
  28. 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
  29. 2016Marr Revisited: 2D-3D Alignment via Surface Normal Predictioncited by 34
  30. 2020Surface Normal Estimation of Tilted Images via Spatial Rectifiercited by 34
  31. 2019FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Imagecited by 26
  32. 2020Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetrycited by 24
  33. 2020Dynamic Plane Convolutional Occupancy Networkscited by 24
  34. 2020Deep Optimized Priors for 3D Shape Modeling and Reconstructioncited by 20
  35. 2020Coupling Explicit and Implicit Surface Representations for Generative 3D Modelingcited by 19
  36. 2021Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wildcited by 19
  37. 2020DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfacescited by 16
  38. 2020Learning Occupancy Function from Point Clouds for Surface Reconstructioncited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2.

5 papers.

  1. 2024Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solvingcited by 19
  2. 2023Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterpartscited by 18
  3. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  4. 2023Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloudcited by 6
  5. 2023DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learningcited by 1