mlsanityData to 14 Oct 2026

BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration

arXiv 2609.11472 ↗First posted 10 Sep 2026cs.CVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Reliable matching between partially observed, deforming point clouds requires global context and fine geometric detail. Coarse candidate selection can exclude correct fine-level correspondences. We present paper, a unified conditional transport framework with the matching matrix itself as the evolving state. Coarse diffusion establishes global matching hypotheses; hierarchy-preserving lifting expands them into a structured high-resolution source. Geometry-conditioned ODE and SDE bridges continue refinement in the complete fine-level candidate space, allowing coarse errors to be corrected. The deterministic endpoint-parameterized conditional flow matching (CFM) design improves matching through iteration, while the SDE forward drift enables effective few-step refinement. Experiments on 4DMatch and 4DLoMatch demonstrate competitive matching and non-rigid registration, with transfer to CAPE and DeepDeform without target-domain training.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 46 of its 59 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

46 of 59 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching1 Dec
  2. 2025RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning26 Jul
  3. 2025BridgeShape: Latent Diffusion Schr"odinger Bridge for 3D Shape Completion29 Jun
  4. 2023Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration31 Dec
  5. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation26 Oct

Other references · 41

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  5. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 602
  6. 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 292
  7. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  8. 2023Flow Matching on General Geometriescited by 265
  9. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 202
  10. 2020D3Feat: Joint Learning of Dense Detection and Description of 3D Local Featurescited by 177
  11. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  12. 2020FLOT: Scene Flow on Point Clouds Guided by Optimal Transportcited by 129
29 more
  1. 2020Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondencecited by 125
  2. 2021Neural Scene Flow Priorcited by 91
  3. 2021Lepard: Learning partial point cloud matching in rigid and deformable scenescited by 85
  4. 2022RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networkscited by 72
  5. 2023Rotation-Invariant Transformer for Point Cloud Matchingcited by 69
  6. 2022Non-rigid Point Cloud Registration with Neural Deformation Pyramidcited by 42
  7. 2019PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Cloudscited by 38
  8. 2023Dynamic Point Fieldscited by 37
  9. 2021Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronizationcited by 30
  10. 2024PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registrationcited by 18
  11. 2024P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoisingcited by 18
  12. 2023Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registrationcited by 15
  13. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  14. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  15. 2025TurboReg: TurboClique for Robust and Efficient Point Cloud Registrationcited by 13
  16. 2024Boundary Constraint-free Biomechanical Model-Based Surface Matching for Intraoperative Liver Deformation Correctioncited by 12
  17. 2022Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulationcited by 10
  18. 2025BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenescited by 8
  19. 2025Progressive Correspondence Regenerator for Robust 3D Registrationcited by 5
  20. 2024A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registrationcited by 4
  21. 2025Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropycited by 4
  22. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  23. 2025FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)N Diffusion Refinementcited by 3
  24. 2024Incremental Multiview Point Cloud Registration with Two-stage Candidate Retrievalcited by 2
  25. 2026SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularizationcited by 2
  26. 2026UniCorrn: Unified Correspondence Transformer Across 2D and 3Dcited by 2
  27. 2025ERNet: Efficient Non-Rigid Registration Network for Point Sequencescited by 1
  28. 2026Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimizationcited by 1
  29. 2026Ordered Diffusion for 3D Human Registrationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration
  2. 2024Diff-Reg v1: Diffusion Matching Model for Registration Problem
  3. 2026Rectified Schr"odinger Bridge Matching for Few-Step Visual Navigation
  4. 2024Learning Diffeomorphism for Image Registration with Time-Continuous Networks using Semigroup Regularization
  5. 2025Denoising Functional Maps: Diffusion Models for Shape Correspondence
  6. 2025A Unified Framework for Diffusion Bridge Problems: Flow Matching and Schr"odinger Matching into One
  7. 2025MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration
  8. 2025Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior