Research map / 3D vision / Face and shape
NeUDF: Learning Neural Unsigned Distance Fields With Volume Rendering
Yutao Liu, Li Wang, Jie Yang, Weikai Chen, Xiaoxu Meng, Bo Yang, Lin Gao
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 |
|---|---|---|---|
| use the proposed UDF volume renderer instead of naive abs(SDF) NeuS extension (ablation) | NeUDF · open surface samples | Chamfer Distance: 9.53 -> 1.49 | Improved |
| use varsigma = x/(1+x) instead of candidate functions (ablation) | NeUDF · diverse shapes | Chamfer Distance: 1.13 -> 1.11 | Improved |
| use varsigma = x/(1+x) instead of candidate functions (ablation) | NeUDF · diverse shapes | Chamfer Distance: 1.18 -> 1.11 | Improved |
| add importance point sampling (ablation) | NeUDF · diverse shapes | Chamfer Distance | Improved |
| add normal regularization (ablation) | NeUDF · diverse shapes | Chamfer Distance | Improved |
| add Eikonal loss (ablation) | NeUDF · diverse shapes | surface quality | Improved |
| replace SDF with UDF representation | NeUDF vs HF-NeuS · open surface datasets (MGN, DF3D) | mean Chamfer Distance: 15.58 -> 8.60 | Improved |
| replace SDF with UDF representation | NeUDF vs NeuS · DTU | Chamfer Distance: 4.46 -> 4.98 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HF-NeuS — HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022) · better on 8 of 8 shared results
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.91)
- NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction (NeurIPS 2024 · similarity 0.90)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.90)
- 2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images (CVPR 2024 · similarity 0.90)
- Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction (AAAI 2025 · similarity 0.90)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 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.
