Research map / 3D vision / Face and shape
ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging
Jiancheng Yang, Udaranga Wickramasinghe, Bingbing Ni, Pascal Fua
Check 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 multiple templates with deformation instead of deformation from a single template (ablation) | ImplicitAtlas · Liver (K) | DSC: 98.22 -> 98.58 | Improved |
| Use multiple templates with deformation instead of deformation from a single template (ablation) | ImplicitAtlas · Pancreas (U) | DSC: 90.61 -> 93.38 | Improved |
| Use multiple static templates rather than a single static template (ablation) | ImplicitAtlas · Liver (K) | DSC: 82.65 -> 98.58 | Improved |
| Add Laplacian Smoothness regularization (ablation) | ImplicitAtlas with deformation and multiple templates · Hippocampus (U) | NSD: 76.99 -> 77.01 | Improved |
| Add Laplacian Smoothness regularization (ablation) | ImplicitAtlas with deformation and multiple templates · Pancreas (U) | DSC: 93.38 -> 93.01 | Hurt |
| Add Deformation Penalty regularization (ablation) | ImplicitAtlas with deformation and multiple templates · Hippocampus (U) | DSC: 93.54 -> 93.79 | Improved |
| Add Deformation Penalty regularization (ablation) | ImplicitAtlas with deformation and multiple templates · Pancreas (U) | NSD: 81.11 -> 82.04 | Improved |
| Add Laplacian Smoothness and Deformation Penalty regularization (ablation) | ImplicitAtlas · Liver (K) | DSC: 98.58 -> 98.50 | Hurt |
| Add Laplacian Smoothness and Deformation Penalty regularization (ablation) | ImplicitAtlas · Liver (U) | NSD: 85.95 -> 86.90 | Improved |
| Replace the MLP decoder with a convolutional decoder | Implicit shape representation · Liver (U) | NSD: 71.23 -> 86.12 | Improved |
| Use ImplicitAtlas instead of the convolutional decoder baseline | Implicit shape representation · Hippocampus (U) | NSD: 75.87 -> 76.99 | Improved |
| Use ImplicitAtlas instead of the convolutional decoder baseline | Implicit shape representation · Liver (U) | DSC: 96.61 -> 96.59 | No clear effect |
Closest papers by meaning
- Deep Implicit Templates for 3D Shape Representation (CVPR 2021 · similarity 0.88)
- Learning Conditional Deformable Templates with Convolutional Networks (NeurIPS 2019 · similarity 0.88)
- Learning Shape Templates With Structured Implicit Functions (ICCV 2019 · similarity 0.88)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.86)
- $\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation (ICLR 2024 · similarity 0.85)
- DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image (CVPR 2025 · similarity 0.84)
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.
