Research map / 3D vision / Face and shape
NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces With Arbitrary Topologies
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 an unsigned distance field with the proposed volume-rendering density | NeuralUDF · DeepFashion3D | Chamfer Distance (10^-3): 1.97 vs. 4.36 | Helped |
| use an unsigned distance field instead of the strongest DTU baseline | NeuralUDF · DTU | Chamfer Distance: 0.68 vs. 0.75 | Hurt |
| add gradient-aware masking to the visibility indicator (ablation) | NeuralUDF · Skull reconstruction | Chamfer Distance: 1.31 -> 0.75 | Helped |
| add the patch blending loss (ablation) | NeuralUDF · NeuralUDF reconstruction | Chamfer Distance: 0.75 -> 0.66 | Helped |
| add the iso-surface regularizer (ablation) | NeuralUDF · NeuralUDF reconstruction | surface quality | Helped |
Closest papers by meaning
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.91)
- 2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images (CVPR 2024 · similarity 0.90)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.90)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.90)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 2025 · similarity 0.90)
- Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction (AAAI 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.