Research map / 3D vision / Face and shape
Learning Signed Distance Field for Multi-View Surface Reconstruction
Jingyang Zhang, Yao Yao, Long Quan
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 feature loss L_F (ablation) | MVSDF (distance only) · DTU | Chamfer distance (mm): 3.56 -> 1.75 | Improved |
| add render loss L_R (ablation) | MVSDF (distance only) · DTU | Chamfer distance (mm): 3.56 -> 1.06 | Improved |
| add render loss on top of feature loss (ablation) | MVSDF · DTU | Chamfer distance (mm): 1.75 -> 0.88 | Improved |
| add feature loss on top of render loss (ablation) | MVSDF · DTU | Chamfer distance (mm): 1.06 -> 0.88 | Improved |
| use lower-resolution MVS depth maps (ablation) | MVSDF · DTU | Chamfer distance (mm): 0.88 -> 0.89 | No clear effect |
| use precomputed geometrically filtered depth maps (ablation) | MVSDF · DTU | Chamfer distance (mm): 0.88 -> 0.88 | No clear effect |
| use MVSDF instead of IDR without masks | IDR · DTU | PSNR: 23.20 -> 25.92 | Improved |
| use MVSDF instead of Vis-MVSNet | Vis-MVSNet · DTU | Chamfer distance (mm): 0.88 -> 0.88 | No clear effect |
| use MVSDF instead of IDR | IDR · EPFL | Chamfer distance (x10^-2): 25.30 -> 6.61 | Improved |
| use MVSDF instead of Vis-MVSNet | Vis-MVSNet · Tanks and Temples | PSNR: 19.56 -> 24.54 | Improved |
Closest papers by meaning
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.90)
- NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation (CVPR 2024 · similarity 0.89)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.89)
- Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set (NeurIPS 2024 · similarity 0.89)
- S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields (NeurIPS 2026 · similarity 0.89)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.89)
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.
