Research map / Point clouds / Shape and surface completion
Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment
Baorui Ma, Junsheng Zhou, Yu-Shen Liu, Zhizhong Han
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 level set alignment loss to NeuralPull | NeuralPull · 3D Scene | CD: 0.059 -> 0.020 | Improved |
| add level set alignment loss to NeuS | NeuS · DTU | Chamfer distance: 0.87 -> 0.78 | Improved |
| add level set alignment loss to MonoSDF | MonoSDF · ScanNet | F-score: 0.733 -> 0.750 | Improved |
| increase alpha from 0 to 0.01, then increase it to 1.0 (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.586 -> 0.394 -> 0.601 | Mixed |
| add adaptive per-query weighting rather than using no weight (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.455 -> 0.394 | Improved |
| use inferred signed distance for adaptive weights instead of point-cloud Euclidean distance (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.394 vs 0.391 | No clear effect |
| use decay parameter delta 10 rather than 1 or 100 (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.439 -> 0.394; 0.394 -> 0.489 | Mixed |
| use current zero-level-set projections instead of fixed nearest surface points (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 1.384 -> 0.394 | Improved |
| use cosine distance instead of MSE on normalized gradients (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.486 -> 0.394 | Improved |
| use cosine distance instead of MSE on unnormalized gradients (ablation) | NeuralPull with level set alignment · 3D Scene | CD×100: 0.494 -> 0.394 | Improved |
| use cosine level-set alignment instead of the DiGS second-order constraint (ablation) | NeuralPull · 3D Scene | CD×100: 0.601 -> 0.394 | Improved |
Closest papers by meaning
- Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection (ICCV 2023 · similarity 0.90)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (CVPR 2024 · similarity 0.89)
- Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors (NeurIPS 2024 · similarity 0.88)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.87)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.87)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 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.
