Research map / 3D vision / Face and shape
Representing 3D Shapes With Probabilistic Directed Distance Fields
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 |
|---|---|---|---|
| Represent shape with DDFs rather than the matched PC-SIREN point-cloud decoder | Single-image reconstruction · ShapeNet Cars | Chamfer distance (× 1000): 0.768 -> 0.606 | Helped |
| Represent shape with DDFs rather than the matched PC-SIREN point-cloud decoder | Single-image reconstruction · ShapeNet Chairs | Chamfer distance (× 1000): 0.915 -> 0.919 | Hurt |
| Represent shape with DDFs rather than the matched PC-SIREN point-cloud decoder | Single-image reconstruction · ShapeNet Cars | F-score at τ: 50.04 -> 52.47 | Helped |
| Remove U-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), U-type test samples: 0.45 -> 0.58 | Hurt |
| Remove A-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), A-type test samples: 0.75 -> 0.82 | Hurt |
| Remove B-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), B-type test samples: 0.19 -> 0.20 | Hurt |
| Remove O-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), O-type test samples: 0.50 -> 0.56 | Hurt |
| Remove T-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), T-type test samples: 0.77 -> 0.84 | Hurt |
| Remove S-type samples from training (ablation) | DDF shape fitting · Stanford Bunny | Minimum distance error (L1; × 10), S-type test samples: 0.67 -> 1.43 | Hurt |
Closest papers by meaning
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.90)
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.89)
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision (CVPR 2020 · similarity 0.89)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.87)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.87)
- Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features (CVPR 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.