Research map / 3D vision / Gaussian splatting
Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction
Zhirui Gao, Renjiao Yi, Yaqiao Dai, Xuening Zhu, Wei Chen, Chenyang Zhu, Kai Xu
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 curve merging (ablation) | Ours · ABC-NEF (DexiNed) | N_sum: 71.7 -> 28.9 | Improved |
| add curve merging (ablation) | Ours · ABC-NEF (DexiNed) | F5: 74.4 -> 73.7 | Hurt |
| add curve splitting (ablation) | Ours · ABC-NEF (DexiNed) | F5: 73.4 -> 73.7 | Improved |
| add straight-line fitting (ablation) | Ours · ABC-NEF (DexiNed) | F5: 68.4 -> 73.7 | Improved |
| add straight-line fitting (ablation) | Ours · ABC-NEF (DexiNed) | Acc.: 8.5 -> 8.2 | Improved |
| add connection loss (ablation) | Ours · ABC-NEF (DexiNed) | F5: 73.2 -> 73.7 | Improved |
| add smoothness loss (ablation) | Ours · ABC-NEF (DexiNed) | Acc.: 8.4 -> 8.2 | Improved |
| add masking loss (ablation) | Ours · ABC-NEF (DexiNed) | Acc.: 8.9 -> 8.2 | Improved |
| add masking loss (ablation) | Ours · ABC-NEF (DexiNed) | F5: 76.1 -> 73.7 | Hurt |
| add masking loss (ablation) | Ours · ABC-NEF (DexiNed) | N_sum: 35.4 -> 28.9 | Improved |
| use direct parametric curve optimization instead of EdgeGaussians | EdgeGaussians · MV2Cyl real objects | F10: 56.7 -> 73.1 | Improved |
| use direct parametric curve optimization instead of EdgeGaussians | EdgeGaussians · ABC-NEF | N_sum: 97.9 -> 28.9 | Improved |
Closest papers by meaning
- SGCR: Spherical Gaussians for Efficient 3D Curve Reconstruction (CVPR 2025 · similarity 0.90)
- Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity (AAAI 2025 · similarity 0.88)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.87)
- UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering (NeurIPS 2026 · similarity 0.87)
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization (CVPR 2025 · similarity 0.87)
- Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
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.
