Research map / Point clouds / Shape and surface completion
Neural Unsigned Distance Fields for Implicit Function Learning
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 |
|---|---|---|---|
| Predict unsigned distance (NDF) instead of occupancy decoding (IF-Net) | IF-Net encoder · ShapeNet Cars closed, 3000 points | Chamfer-L2 mean (x1e-4): 0.326 -> 0.127 | Helped |
| Train on raw unclosed cars with inner structures instead of closed meshes | NDF · ShapeNet Cars, 3000 points | Chamfer-L2 mean (x1e-4): 0.127 -> 0.275 | Mixed |
| Use NDF (unsigned distance) instead of SAL (signed output) on raw cars | raw-trained implicit model · ShapeNet raw Cars, 3000 points | Chamfer-L2 mean (x1e-4): 7.39 -> 0.275 | Helped |
Closest papers by meaning
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.92)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.91)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.90)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 2025 · similarity 0.89)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.89)
- High Resolution UDF Meshing via Iterative Networks (NeurIPS 2025 · similarity 0.89)
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.