Research map / Point clouds / Shape and surface completion
OscuFit: Learning to Fit Osculating Implicit Quadrics for Point Clouds
Rao Fu, Qian Li, Liang Yu, Jianmin Zheng
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 |
|---|---|---|---|
| add L_n, L_g, L_m on top of L_f (all four losses) (ablation) | OscuFit · ABC-Diff average | Normal RMSE (x10): 1.30 -> 1.26 | Improved |
| add L_n, L_g, L_m on top of L_f (all four losses) (ablation) | OscuFit · ABC-Diff average | Gaussian curvature RMSE: 0.33 -> 0.27 | Improved |
| add L_n, L_g, L_m on top of L_f (all four losses) (ablation) | OscuFit · ABC-Diff average | Mean curvature RMSE: 0.80 -> 0.69 | Improved |
| add fitting loss L_f to normal and curvature losses (ablation) | OscuFit · ABC-Diff average | Normal RMSE (x10): 1.35 -> 1.26 | Improved |
| supervise with L_f instead of L_n only (ablation) | OscuFit · ABC-Diff average | Normal RMSE (x10): 1.39 -> 1.30 | Improved |
| supervise with L_f instead of L_n only (ablation) | OscuFit · ABC-Diff average | Mean curvature RMSE: 0.96 -> 0.80 | Improved |
| supervise with L_f instead of L_n only (ablation) | OscuFit · ABC-Diff average | Gaussian curvature RMSE: 0.31 -> 0.33 | Hurt |
| increase patch size K from 128 to 256 (ablation) | OscuFit · ABC-Diff average | Normal RMSE (x10): 1.36 -> 1.26 | Improved |
| increase patch size K from 64 to 256 (ablation) | OscuFit · ABC-Diff average | Normal RMSE (x10): 1.88 -> 1.26 | Improved |
| increase patch size K from 64 to 256 (ablation) | OscuFit · ABC-Diff average | Gaussian curvature RMSE: 0.62 -> 0.27 | Improved |
| use OscuFit instead of GraphFit | GraphFit · ABC-Diff clean | Normal RMSE (x10): 0.55 -> 0.45 | Improved |
| use OscuFit instead of GraphFit | GraphFit · ABC-Diff 1.2% noise | Mean curvature RMSE: 0.90 -> 0.82 | Improved |
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.
- GraphFit — GraphFit: Learning Multi-Scale Graph-Convolutional Representation for Point Cloud Normal Estimation (ECCV 2022) · better on 10 of 10 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
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.86)
- OffsetOPT: Explicit Surface Reconstruction without Normals (CVPR 2025 · similarity 0.86)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.86)
- SurGe: Improved Surface Geometry in Point Maps (NeurIPS 2026 · similarity 0.86)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.86)
- An Explicit Frame Construction for Normalizing 3D Point Clouds (ICML 2024 · 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.
