Research map / Point clouds / Shape and surface completion
FlexPara: Flexible Neural Surface Parameterization
Yuming Zhao, Qijian Zhang, Junhui Hou, Jiazhi Xia, Wenping Wang, Ying He
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 differential distortion loss (DDL) (ablation) | FlexPara global · Giraffe | conformal distortion: 0.424 -> 0.071 | Improved |
| add triangle distortion loss (TDL) (ablation) | FlexPara global · Giraffe | conformal distortion: 0.088 -> 0.071 | Improved |
| add bottom 3D-2D-3D branch (ablation) | FlexPara global · Giraffe | conformal distortion: 0.209 -> 0.071 | Improved |
| add upper 2D-3D-2D branch (ablation) | FlexPara global · Giraffe | conformal distortion: 0.075 -> 0.071 | Improved |
| add bi-directional branches to multi-chart framework (ablation) | FlexPara multi-chart · Bear | training time (hours): 0.34 -> 1.53 | Hurt |
| add DDL-style multi-loss to multi-chart framework (ablation) | FlexPara multi-chart · Bear | training time (hours): 0.34 -> 8.95 | Hurt |
| add bi-directional branches to multi-chart framework (ablation) | FlexPara multi-chart · Fish | isometric distortion x1e-4: 21.4 -> 52.3 | Mixed |
| use FlexPara instead of OptCuts | global parameterization · Torus-knot | conformality error: 0.7320 -> 0.0150 | Improved |
| use FlexPara instead of Nuvo | multi-chart parameterization · Bunny | isometric distortion x1e-4: 59.6 -> 6.4 | Improved |
| use FlexPara instead of FBCP-PC | point cloud global parameterization · Spiral-pts | conformality error: 0.023 -> 0.098 | Hurt |
| switch GPU from RTX3090 to H800 | FlexPara · runtime scalability | efficiency: about 75% | Improved |
| switch GPU from RTX3090 to RTX5090 | FlexPara · runtime scalability | efficiency: approximately 20% | 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.
- SLIM — SLIM: Self-Supervised LiDAR Scene Flow and Motion Segmentation (ICCV 2021) · better on 4 of 4 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
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.94)
- Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering (ECCV 2024 · similarity 0.89)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.86)
- Improving Neural Network Surface Processing with Principal Curvatures (NeurIPS 2024 · similarity 0.86)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.86)
- M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals (NeurIPS 2026 · similarity 0.85)
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.
