Research map / 3D vision / Depth and stereo
Semantic 3D Reconstruction With Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint
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 the proposed visibility-consistent ray-potential formulation instead of its direct convex relaxation (ablation) | Dense 3D reconstruction · Lemon dataset | energy: 431893 versus 626614 | Mixed |
| Use continuous surface-area regularization with true ray potentials | Middlebury multi-view stereo · Dino Full and Dino Ring | accuracy | Helped |
| Use true ray potentials rather than unary-potential approximation | Semantic 3D reconstruction · Real-world semantic reconstruction datasets | surface detail | Helped |
| Use the proposed ray-potential representation on thin surfaces | Dense 3D reconstruction · Street sign dataset | thin-surface reconstruction | Helped |
| Approximate the ray data cost with unary potentials | Semantic 3D reconstruction · Real-world semantic reconstruction datasets | surface detail | Hurt |
| Use the discrete graph-based ray-potential approach | Semantic 3D reconstruction · Real-world semantic reconstruction datasets | surface smoothness | Hurt |
| Use the coarse-to-fine scheme | Savinov et al. 2015 · Semantic 3D reconstruction | reconstruction artifacts | Hurt |
Closest papers by meaning
- Semantic Multi-View Stereo: Jointly Estimating Objects and Voxels (CVPR 2017 · similarity 0.88)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.87)
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (CVPR 2025 · similarity 0.86)
- SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization (AAAI 2024 · similarity 0.85)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.85)
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation (NeurIPS 2026 · similarity 0.85)
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.