Research map / 3D vision / Face and shape
Marching-Primitives: Shape Abstraction From Signed Distance Function
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MPS instead of NB | Shape abstraction from SDF · ShapeNet test set | Chamfer-L1: 0.028 -> 0.022 | Helped |
| Use MPS instead of NB | Shape abstraction from SDF · ShapeNet test set | IoU: 0.674 -> 0.870 | Helped |
| Use superquadrics instead of ellipsoids (ablation) | Marching-Primitives · ShapeNet test set | Chamfer-L1: 0.024 -> 0.022 | Helped |
| Use superquadrics instead of ellipsoids (ablation) | Marching-Primitives · ShapeNet test set | IoU: 0.793 -> 0.870 | Helped |
| Increase input voxel-grid resolution (ablation) | Marching-Primitives · Armadillo | Chamfer-L1 | Helped |
| Decrease the SDF truncation threshold (ablation) | Marching-Primitives · Armadillo | abstraction accuracy | Mixed |
Closest papers by meaning
- Shape Abstraction via Marching Differentiable Support Functions (CVPR 2025 · similarity 0.88)
- S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields (NeurIPS 2026 · similarity 0.86)
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (CVPR 2019 · similarity 0.85)
- 3PSDF: Three-Pole Signed Distance Function for Learning Surfaces With Arbitrary Topologies (CVPR 2022 · similarity 0.85)
- Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives (NeurIPS 2023 · similarity 0.85)
- GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation (ICLR 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.