Research map / Point clouds / Shape and surface completion
Bilateral Normal Integration
Xu Cao, Hiroaki Santo, Boxin Shi, Fumio Okura, Yasuyuki Matsushita
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| use bilaterally weighted semi-smooth functional instead of smooth-surface IPF | IPF · Synthetic orthographic (analytic normal map) | MADE: 0.254 -> 0.001 | Improved |
| use bilaterally weighted semi-smooth functional instead of AD | AD · Synthetic orthographic (Mitsuba-rendered Reading) | MADE: 0.166 -> 0.018 | Improved |
| use BiNI instead of AD | AD · Synthetic orthographic (analytic normal map) | MADE: 0.220 -> 0.001 | Improved |
| use BiNI in the perspective case instead of IPF | IPF · Synthetic perspective (Stanford Bunny) | MADE: 3.08 -> 0.45 | Improved |
| use BiNI in the perspective case instead of TV/RE/MS/AD (which stay at initialization) | TV, RE, MS, AD · Synthetic perspective (Stanford Bunny) | MADE: 4.02 -> 0.45 | Improved |
| use BiNI instead of IPF | IPF · DiLiGenT perspective (Cow) | MADE: 0.89 -> 0.07 | Improved |
| use BiNI instead of IPF | IPF · DiLiGenT perspective (Goblet) | MADE: 11.64 -> 8.53 | Improved |
| use BiNI instead of IPF | IPF · DiLiGenT perspective (Harvest) | MADE: 10.11 -> 2.73 | Improved |
| use robust estimators/diffusion (TV, RE, MS, AD) with traditional formulation in perspective case | TV, RE, MS, AD · Synthetic perspective (Stanford Bunny) | MADE: 4.02 -> 4.01 | No clear effect |
Closest papers by meaning
- Discontinuity-preserving Normal Integration with Auxiliary Edges (CVPR 2024 · similarity 0.92)
- Surface Reconstruction From Normals: A Robust DGP-Based Discontinuity Preservation Approach (CVPR 2019 · similarity 0.91)
- Discontinuity-aware Normal Integration for Generic Central Camera Models (ICCV 2025 · similarity 0.90)
- Variational Graph-based Normal Integration (CVPR 2026 · similarity 0.89)
- Feature-Preserving Mesh Decimation for Normal Integration (CVPR 2025 · similarity 0.85)
- PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction (CVPR 2025 · similarity 0.83)
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.
