Research map / 3D vision / Face and shape
NeUDF: Leaning Neural Unsigned Distance Fields With Volume Rendering
Yu-Tao 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 UDF-based rendering with dedicated UDF weight formulations instead of the naive NeuS-to-UDF extension | Multi-view reconstruction · Open surface samples | Chamfer Distance: 9.53 vs 1.49 | Improved |
| Use the dedicated importance-sampling weight rather than the rendering weight for sampling (ablation) | NeUDF · Open-surface reconstruction examples | Chamfer Distance | Improved |
| Add normal regularization (ablation) | NeUDF · Open-surface reconstruction examples | Chamfer Distance | Improved |
| Add Eikonal loss (ablation) | NeUDF · Complex surface reconstruction examples | Chamfer Distance | Improved |
| Use x/(1+x) rather than the alternative rendering CDF candidates (ablation) | NeUDF · Diverse shapes | Chamfer Distance: ours: 1.11 vs candidates: 1.13/1.18 | Improved |
| Use alternative valid rendering CDFs instead of x/(1+x) (ablation) | NeUDF · UDF reconstruction after 300k iterations | Chamfer Distance: 1.11 vs 1.13/1.18 | Hurt |
Later papers that compared with this method
4 later accepted papers report NeUDF as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- VRP-UDF: Toward Unbiased Learning of Unsigned Distance Functions From Multi-View Images With Volume Rendering Priors (TPAMI 2026 · better on 1 of 1 shared result)
- Learning Unsigned Distance Functions from Multi-view Images with Volume Rendering Priors (ECCV 2024 · better on 3 of 3 shared results)
- 2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images (CVPR 2024 · better on 2 of 2 shared results)
- Ghost on the Shell: An Expressive Representation of General 3D Shapes (ICLR 2024 · better on 2 of 2 shared results)
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 1 of 1 shared result
- NeuS — NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (NeurIPS 2021) · better on 1 of 1 shared result
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
- NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction (NeurIPS 2024 · similarity 0.90)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (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 0.89)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.89)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.88)
- Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction (AAAI 2025 · similarity 0.88)
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.
