Research map / Point clouds / Shape and surface completion
DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
Yizhak Ben-Shabat, Stephen Gould
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 a larger neighborhood (k=256 vs 64 points) (ablation) | DeepFit · PCPNet normals, high noise | RMSE | Improved |
| use a larger neighborhood (more points) (ablation) | DeepFit · PCPNet normals, no noise | RMSE | Hurt |
| raise the jet order from 1 to 2-4 (ablation) | DeepFit · PCPNet normals, low and medium noise | RMSE | Mixed |
| vary jet order n=1,2,3,4 (ablation) | DeepFit · PCPNet normals | RMSE | No clear effect |
| use DeepFit weighted fitting instead of single-scale PCPNet | PCPNet · PCPNet normals (average) | RMSE angle error: 14.56 -> 11.8 | Improved |
| use multiple scales instead of one in PCPNet | PCPNet · PCPNet normals (average) | RMSE angle error: 14.56 -> 14.34 | No clear effect |
| use DeepFit instead of PCPNet for maximum curvature | PCPNet · PCPNet curvature k1 | normalized RMSE: 1.38 -> 0.89 | Improved |
| use DeepFit instead of PCPNet for minimum curvature | PCPNet · PCPNet curvature k2 | normalized RMSE: 0.54 -> 0.466 | Improved |
| use DeepFit instead of Lenssen et al. under high noise | Lenssen et al. · PCPNet normals, noise 0.012 | RMSE angle error: 21.96 -> 23.12 | Hurt |
Later papers that compared with this method
7 later accepted papers report DeepFit as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- CAP-UDF: Learning Unsigned Distance Functions Progressively From Raw Point Clouds With Consistency-Aware Field Optimization (TPAMI 2024 · better on 1 of 1 shared result)
- Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation (CVPR 2023 · better on 2 of 2 shared results)
- NeAF: Learning Neural Angle Fields for Point Normal Estimation (AAAI 2023 · better on 1 of 1 shared result)
- HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces (NeurIPS 2022 · better on 2 of 2 shared results)
- GraphFit: Learning Multi-Scale Graph-Convolutional Representation for Point Cloud Normal Estimation (ECCV 2022 · better on 2 of 2 shared results)
- Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds (TPAMI 2022 · better on 1 of 1 shared result)
- AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds (ICCV 2021 · better on 9 of 9 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Nesti-Net — Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks (CVPR 2019) · better on 2 of 2 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
- Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation (CVPR 2023 · similarity 0.91)
- ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds (ECCV 2020 · similarity 0.90)
- AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds (ICCV 2021 · similarity 0.90)
- HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces (NeurIPS 2022 · similarity 0.89)
- NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function (NeurIPS 2023 · similarity 0.89)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 2025 · similarity 0.86)
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.
