mlsanityData to 13 Oct 2026

CorticalFlow: A Diffeomorphic Mesh Deformation Module for Cortical Surface Reconstruction

arXiv 2206.02374 ↗First posted 6 Jun 2022cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. To conserve the template mesh's topological properties, we train our model over a set of diffeomorphic transformations. This new implementation of a flow Ordinary Differential Equation (ODE) framework benefits from a small GPU memory footprint, allowing the generation of surfaces with several hundred thousand vertices. To reduce topological errors introduced by its discrete resolution, we derive numeric conditions which improve the manifoldness of the predicted triangle mesh. To exhibit the utility of CorticalFlow, we demonstrate its performance for the challenging task of brain cortical surface reconstruction. In contrast to current state-of-the-art, CorticalFlow produces superior surfaces while reducing the computation time from nine and a half minutes to one second. More significantly, CorticalFlow enforces the generation of anatomically plausible surfaces; the absence of which has been a major impediment restricting the clinical relevance of such surface reconstruction methods.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 38 of its 82 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

38 of 82 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  5. 2018Neural Ordinary Differential Equationscited by 3,750
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,686
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,039
  8. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 650
  11. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  12. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
26 more
  1. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  2. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  3. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  4. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  5. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  6. 2019CvxNet: Learnable Convex Decompositioncited by 174
  7. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  8. 2019FastSurfer -- A fast and accurate deep learning based neuroimaging pipelinecited by 110
  9. 2020Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networkscited by 107
  10. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  11. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  12. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  13. 2018Learning a Probabilistic Model for Diffeomorphic Registrationcited by 62
  14. 2020Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flowscited by 60
  15. 2018Im2Struct: Recovering 3D Shape Structure from a Single RGB Imagecited by 55
  16. 2019Voxel2Mesh: 3D Mesh Model Generation from Volumetric Datacited by 52
  17. 2020Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidancecited by 39
  18. 2018QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomycited by 37
  19. 2020ShapeFlow: Learnable Deformations Among 3D Shapescited by 28
  20. 2019GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objectscited by 27
  21. 2020DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstructioncited by 26
  22. 2019Region-specific Diffeomorphic Metric Mappingcited by 24
  23. 2021An Effective Loss Function for Generating 3D Models from Single 2D Image without Renderingcited by 7
  24. 20193DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentationcited by 3
  25. 2015Size-optimal Steiner points for Delaunay-refinement on curved surfacescited by 1
  26. 2020A Portable Brain MRI Scanner for Underserved Settings and Point-Of-Care Imagingcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 2.

5 papers.

  1. 2023Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstructioncited by 7
  2. 2023Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstructioncited by 4
  3. 2023SurfNN: Joint Reconstruction of Multiple Cortical Surfaces from Magnetic Resonance Imagescited by 2
  4. 2025Template-Based Cortical Surface Reconstruction with Minimal Energy Deformationcited by 0
  5. 2025FEAorta: A Fully Automated Framework for Finite Element Analysis of the Aorta From 3D CT Imagescited by 0