Research map / 3D vision / Face and shape
SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
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 SDFDiff instead of DSS for multi-view reconstruction | Multi-view 3D reconstruction · Torus | symmetric Hausdorff distance: 0.035398 -> 0.015637 | Helped |
| Use SDFDiff instead of DSS for multi-view reconstruction | Multi-view 3D reconstruction · Bunny | symmetric Hausdorff distance: 0.109432 -> 0.026654 | Helped |
| Use SDFDiff instead of SMVS for multi-view reconstruction | Multi-view 3D reconstruction · Dragon | symmetric Hausdorff distance: 0.097816 -> 0.074723 | Helped |
| Use SDFDiff instead of SoftRas (full) | Single-view reconstruction · ShapeNet 13 categories (Mean) | 3D IoU: 0.6464 -> 0.6674 | Helped |
| Use a lower initial SDF resolution (ablation) | SDFDiff multi-view optimization · Multi-view reconstruction | reconstruction quality | Helped |
| Add more intermediate resolution stages (ablation) | SDFDiff multi-view optimization · Multi-view reconstruction | reconstruction quality | Helped |
| Remove the coarse-to-fine multi-resolution schedule (ablation) | SDFDiff multi-view optimization · Multi-view reconstruction | reconstruction success | Hurt |
| Vary image resolution (ablation) | SDFDiff multi-view optimization · Multi-view reconstruction | reconstruction quality | No clear effect |
| Add Gaussian noise to target views or camera poses (ablation) | SDFDiff multi-view optimization · Noisy multi-view inputs | reconstruction robustness | No clear effect |
Closest papers by meaning
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (CVPR 2019 · similarity 0.91)
- DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing (CVPR 2020 · similarity 0.91)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.89)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.88)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.87)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 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.