Research map / 3D vision / Face and shape
Multi-View Reconstruction Using Signed Ray Distance Functions (SRDF)
Read the paperCheck 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 SRDF-based volumetric depth optimization instead of differentiable rendering | Multi-view 3D reconstruction · DTU | Chamfer Distance: 0.69 -> 0.36 | Helped |
| Use SRDF-based volumetric depth optimization instead of classic MVS | Multi-view 3D reconstruction · DTU | Chamfer Distance: 0.42 -> 0.36 | Helped |
| Use SRDF-based volumetric depth optimization instead of deep MVS | Multi-view 3D reconstruction · DTU | Chamfer Distance: 0.38 -> 0.36 | Helped |
| Use SRDF-based volumetric depth optimization instead of CasMVSNet | Multi-view 3D reconstruction · DTU | Accuracy: 0.34 -> 0.37 | Hurt |
| Use SRDF-based volumetric depth optimization instead of PatchmatchNet | Multi-view 3D reconstruction · DTU | Completeness: 0.35 -> 0.36 | Hurt |
| Use the learned photo-consistency prior instead of the median-color baseline prior | SRDF reconstruction · Real images | reconstruction quality | Helped |
| Use the median-color baseline photo-consistency prior | SRDF reconstruction · Renderpeople synthetic data | reconstruction quality | Helped |
| Optimize PatchmatchNet depth results with SRDF | PatchmatchNet reconstruction · Multi-view human reconstruction | surface detail and noise | Helped |
| Optimize PatchmatchNet depth results with SRDF | PatchmatchNet reconstruction · Multi-view human reconstruction | recovery from large geometric errors | Hurt |
Closest papers by meaning
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.91)
- SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization (CVPR 2020 · similarity 0.90)
- RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency (NeurIPS 2023 · similarity 0.88)
- Differentiable Stereopsis: Meshes From Multiple Views Using Differentiable Rendering (CVPR 2022 · similarity 0.88)
- SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration (CVPR 2024 · similarity 0.86)
- Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images (CVPR 2025 · 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.