Research map / Point clouds / Shape and surface completion
4D Myocardium Reconstruction with Decoupled Motion and Shape Model
Xiaohan Yuan, Cong Liu, Yangang Wang
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 |
|---|---|---|---|
| decouple motion code from shape code (versus DeepSDF/DIT/DIF with coupled codes) | 4D myocardium reconstruction · Proposed dataset (SAX+LAX) | EMD: 6.010 -> 3.603 (vs DIF) | Improved |
| use ours instead of DIF with SAX-only input | 4D myocardium reconstruction · Proposed dataset (SAX) | Chamfer Distance: 2.891 -> 2.634 | Improved |
| add long-axis (LAX) contours to short-axis input for our method | Ours · Proposed dataset | EMD: 6.173 -> 3.603 | Improved |
| add LAX contours to input for baseline methods | DeepSDF and DIF · Proposed dataset | Chamfer Distance: DIF 2.891 -> 2.858; DeepSDF 3.331 -> 2.852 | No clear effect |
| pre-train ED shape model in ED-space then train jointly with motion model (ablation) | ED shape model · training loss curve | loss convergence | Improved |
| apply method to ACDC 2017 (diseased hearts) despite training only on healthy subjects | Ours · ACDC 2017 | Dice: 0.702 -> 0.765 (vs DIT) | Improved |
Closest papers by meaning
- Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging (ICCV 2023 · similarity 0.87)
- Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding (NeurIPS 2024 · similarity 0.82)
- Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI (CVPR 2024 · similarity 0.82)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · similarity 0.82)
- EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function (NeurIPS 2026 · similarity 0.82)
- LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators (NeurIPS 2026 · similarity 0.81)
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.
