mlsanityData to 7 Oct 2026

Registered and Segmented Deformable Object Reconstruction from a Single View Point Cloud

arXiv 2311.07357 ↗First posted 13 Nov 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In deformable object manipulation, we often want to interact with specific segments of an object that are only defined in non-deformed models of the object. We thus require a system that can recognize and locate these segments in sensor data of deformed real world objects. This is normally done using deformable object registration, which is problem specific and complex to tune. Recent methods utilize neural occupancy functions to improve deformable object registration by registering to an object reconstruction. Going one step further, we propose a system that in addition to reconstruction learns segmentation of the reconstructed object. As the resulting output already contains the information about the segments, we can skip the registration process. Tested on a variety of deformable objects in simulation and the real world, we demonstrate that our method learns to robustly find these segments. We also introduce a simple sampling algorithm to generate better training data for occupancy learning.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 40 of its 46 references that are in the map. First posted on arXiv 13 Nov 2023.

Builds on

40 of 46 references.

References · 40

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2020Point Transformercited by 1,462
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  9. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  10. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  11. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  12. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
28 more
  1. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  2. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  3. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  4. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  5. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  6. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  7. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  8. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  9. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  10. 2019CvxNet: Learnable Convex Decompositioncited by 173
  11. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  12. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  13. 2018Deep Geometric Prior for Surface Reconstructioncited by 110
  14. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  15. 2020Learning Deformable Tetrahedral Meshes for 3D Reconstructioncited by 84
  16. 2020Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Datacited by 74
  17. 20213D Semantic Scene Completion: a Surveycited by 74
  18. 2018MeshCNN: A Network with an Edgecited by 69
  19. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  20. 2019RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completioncited by 54
  21. 2021Semantic Scene Completion via Integrating Instances and Scene in-the-Loopcited by 54
  22. 2020Point2Mesh: A Self-Prior for Deformable Meshescited by 41
  23. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  24. 2020Meshlet Priors for 3D Mesh Reconstructioncited by 23
  25. 2020Learning Occupancy Function from Point Clouds for Surface Reconstructioncited by 13
  26. 2020Deep Manifold Priorcited by 9
  27. 2020The Whole Is Greater Than the Sum of Its Nonrigid Partscited by 7
  28. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 0; 2026: 1.

6 papers.

  1. 2024Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Imagescited by 8
  2. 2024LOOC: Localizing Organs using Occupancy Networks and Body Surface Depth Imagescited by 5
  3. 2024LUDO: Low-Latency Understanding of Deformable Objects using Point Cloud Occupancy Functionscited by 4
  4. 2024Tracking Tumors under Deformation from Partial Point Clouds using Occupancy Networkscited by 3
  5. 2024Anatomical Region Recognition and Real-time Bone Tracking Methods by Dynamically Decoding A-Mode Ultrasound Signalscited by 0
  6. 2026Occupancy Network-Guided Autonomous Robotic Partial Nephrectomycited by 0