mlsanityData to 7 Oct 2026

Non-rigid Point Cloud Registration with Neural Deformation Pyramid

arXiv 2205.12796 ↗First posted 25 May 2022cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

Non-rigid point cloud registration is a key component in many computer vision and computer graphics applications. The high complexity of the unknown non-rigid motion make this task a challenging problem. In this paper, we break down this problem via hierarchical motion decomposition. Our method called Neural Deformation Pyramid (NDP) represents non-rigid motion using a pyramid architecture. Each pyramid level, denoted by a Multi-Layer Perception (MLP), takes as input a sinusoidally encoded 3D point and outputs its motion increments from the previous level. The sinusoidal function starts with a low input frequency and gradually increases when the pyramid level goes down. This allows a multi-level rigid to nonrigid motion decomposition and also speeds up the solving by 50 times compared to the existing MLP-based approach. Our method achieves advanced partialto-partial non-rigid point cloud registration results on the 4DMatch/4DLoMatch benchmark under both no-learned and supervised settings.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 25 May 2022.

Builds on

23 of 45 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  8. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  9. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  11. 2020Deep Global Registrationcited by 228
  12. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
11 more
  1. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
  2. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  3. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  4. 2021Neural Scene Flow Priorcited by 91
  5. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  6. 2019DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Datacited by 76
  7. 2021SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimizationcited by 59
  8. 2020Neural Non-Rigid Trackingcited by 49
  9. 2019PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Cloudscited by 38
  10. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  11. 2020Learning to Optimize Non-Rigid Trackingcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 11; 2025: 13; 2026: 8.

41 papers.

Sort:

By area:

  1. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 81
  2. 2023Dynamic Point Fieldscited by 37
  3. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 14
  4. 2022Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimizationcited by 12
  5. 2023Non-Rigid Shape Registration via Deep Functional Maps Priorcited by 12
  6. 2024SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimationcited by 12
  7. 2024Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysiscited by 10
  8. 2024DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Featurescited by 10
  9. 2023Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videoscited by 8
  10. 2024DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstructioncited by 8
  11. 2025Category-Agnostic Neural Object Riggingcited by 8
  12. 2025Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondencecited by 7
29 more
  1. 2025Landmark-Free Preoperative-to-Intraoperative Registration in Laparoscopic Liver Resectioncited by 7
  2. 2023Leveraging Intrinsic Properties for Non-Rigid Garment Alignmentcited by 6
  3. 2026Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Modelscited by 6
  4. 2023ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistencycited by 5
  5. 2023Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networkscited by 4
  6. 2024Degrees of Freedom Matter: Inferring Dynamics from Point Trajectoriescited by 4
  7. 2025Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropycited by 4
  8. 2026Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunitiescited by 4
  9. 2024Diff-Reg v1: Diffusion Matching Model for Registration Problemcited by 3
  10. 2025Toward Reliable AR-Guided Surgical Navigation: Interactive Deformation Modeling with Data-Driven Biomechanics and Promptscited by 3
  11. 2023Non-rigid Point Cloud Registration for Middle Ear Diagnostics with Endoscopic Optical Coherence Tomographycited by 2
  12. 2024Prim2Room: Layout-Controllable Room Mesh Generation from Primitivescited by 2
  13. 2025DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformationcited by 2
  14. 2025FUSE: A Flow-based Mapping Between Shapescited by 2
  15. 2024SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registrationcited by 1
  16. 2024COSMU: Complete 3D human shape from monocular unconstrained imagescited by 1
  17. 2025Preconditioned Deformation Gridscited by 1
  18. 2025ERNet: Efficient Non-Rigid Registration Network for Point Sequencescited by 1
  19. 2026Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequencescited by 1
  20. 2026DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registrationcited by 1
  21. 2024SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registrationcited by 0
  22. 2025NFR: Neural Feature-Guided Non-Rigid Shape Registrationcited by 0
  23. 2025PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigationcited by 0
  24. 2025SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splattingcited by 0
  25. 2025Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentationcited by 0
  26. 2026One-shot Compositional 3D Head Avatars with Deformable Haircited by 0
  27. 2026MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequencescited by 0
  28. 2026BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registrationcited by 0
  29. 2026Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformationcited by 0