Research map / Point clouds / Shape and surface completion
Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging
Meng Ye, Dong Yang, Mikael Kanski, Leon Axel, Dimitris Metaxas
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use coarse-to-fine NDM instead of template-registration MR-Net | NDM · ED reconstruction | Chamfer distance (mm): 3.09 -> 2.73 | Improved |
| train NDM supervised from shape manifold instead of unsupervised on sparse input | NDM · ED reconstruction | Chamfer distance (mm): 5.16 -> 2.73 | Improved |
| add L_d (local deformation magnitude loss) on top of no regularization (ablation) | NDM · ED reconstruction | Chamfer distance (mm): 4.49 -> 3.15 | Improved |
| add L_s (smoothness loss) on top of no regularization (ablation) | NDM · ED reconstruction | self-intersection ratio: 0.049 -> 0.001 | Improved |
| add both L_d and L_s (ablation) | NDM · ED reconstruction | Chamfer distance (mm): 4.49 -> 2.73 | Improved |
| add L_d alone without L_s (ablation) | NDM · ED reconstruction | self-intersection ratio: 0.049 -> 0.049 | No clear effect |
| use NDM learned dense correspondence for registration versus baselines | NDM · ED to ES registration | Chamfer distance (mm): 2.44 -> 1.94 | Improved |
Closest papers by meaning
- 4D Myocardium Reconstruction with Decoupled Motion and Shape Model (ICCV 2023 · similarity 0.87)
- Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow (CVPR 2022 · similarity 0.86)
- Learning Deformable Image Registration From Optimization: Perspective, Modules, Bilevel Training and Beyond (TPAMI 2021 · similarity 0.86)
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation (CVPR 2025 · similarity 0.83)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.83)
- DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
