Research map / 3D vision / Depth and stereo
Neural 3D Scene Reconstruction With the Manhattan-World Assumption
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 |
|---|---|---|---|
| add estimated-depth supervision to VolSDF (ablation) | VolSDF · ScanNet | F-score: 0.346 -> 0.431 | Helped |
| add geometric normal loss to VolSDF-D (ablation) | VolSDF-D · ScanNet | F-score: 0.431 -> 0.438 | Helped |
| learn semantics in 3D space (ablation) | VolSDF-D · ScanNet | F-score: 0.431 -> 0.474 | Helped |
| replace the geometric normal loss with the joint semantic-geometry loss (ablation) | VolSDF-D-G · ScanNet | F-score: 0.438 -> 0.602 | Helped |
| use ManhattanSDF instead of ACMP | 3D reconstruction · ScanNet | F-score: 0.555 -> 0.602 | Helped |
| use ManhattanSDF instead of ACMP | 3D reconstruction · 7-Scenes | F-score: 0.299 -> 0.336 | Helped |
| jointly learn 3D semantics with geometry | DeepLabV3+ semantic predictions · ScanNet | mean IoU: 0.503 -> 0.571 | Helped |
Closest papers by meaning
- PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting (NeurIPS 2025 · similarity 0.89)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (CVPR 2025 · similarity 0.87)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.87)
- NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation (CVPR 2024 · similarity 0.87)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · similarity 0.86)
- Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion (CVPR 2024 · 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.