Research map / Point clouds / Shape and surface completion
DeepCurrents: Learning Implicit Representations of Shapes With Boundaries
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DeepCurrents instead of the baseline reconstruction method | Single-surface reconstruction · FAUST head | UCD: 0.0049 -> 0.0010 | Helped |
| Use DeepCurrents instead of the baseline reconstruction method | Single-surface reconstruction · FAUST hand | UCD: 0.0045 -> 0.0011 | Helped |
| Use DeepCurrents instead of the baseline reconstruction method | Single-surface reconstruction · FAUST torso | UCD: 0.0049 -> 0.00092 | Helped |
| Use DeepCurrents instead of the baseline reconstruction method | Single-surface reconstruction · FAUST foot | UCD: 0.0055 -> 0.00092 | Helped |
| Add random Fourier feature input projection (ablation) | DeepCurrents surface reconstruction · FAUST hand | learnability | Helped |
| Add the surface loss term (ablation) | DeepCurrents surface reconstruction · FAUST hand | surface recovery | Helped |
| Add boundary weighting to the current loss (ablation) | DeepCurrents surface reconstruction · FAUST hand | boundary sharpness | Helped |
| Use softplus instead of ReLU activations (ablation) | DeepCurrents decoder · FAUST hand | surface sharpness | Helped |
Closest papers by meaning
- Local Deep Implicit Functions for 3D Shape (CVPR 2020 · similarity 0.89)
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.89)
- Learning Manifold Patch-Based Representations of Man-Made Shapes (ICLR 2021 · similarity 0.88)
- Neural Convolutional Surfaces (CVPR 2022 · similarity 0.88)
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (CVPR 2017 · similarity 0.88)
- Implicit Geometric Regularization for Learning Shapes (ICML 2020 · similarity 0.88)
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.
