Research map / 3D vision / Depth and stereo
Indoor Panorama Planar 3D Reconstruction via Divide and Conquer
Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun, Hwann-Tzong Chen
Check 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 the proposed divide-and-conquer method rather than PlaneAE | Indoor panorama planar reconstruction · Matterport3D test | Per-pixel recall: 0.498 -> 0.544 | Improved |
| Use the proposed divide-and-conquer method rather than PlaneAE | Indoor panorama planar reconstruction · Stanford2D3D validation | Per-plane recall: 0.341 -> 0.430 | Improved |
| Use the proposed divide-and-conquer method rather than PlaneAE | Indoor panorama planar reconstruction · Structured3D test | Per-pixel recall: 0.728 -> 0.794 | Improved |
| Add yaw-invariant parameterization (ablation) | V-plane orientation estimation · Stanford2D3D validation | V-plane orientation error (deg): 7.29 -> 5.18 | Improved |
| Add CoordConv to yaw-invariant parameterization (ablation) | V-plane orientation estimation · Stanford2D3D validation | V-plane orientation error (deg): 5.18 -> 5.21 | No clear effect |
| Add yaw-invariant parameterization (ablation) | PlaneRCNN · Stanford2D3D validation | Per-pixel recall: 0.452 -> 0.481 | Improved |
| Add yaw-invariant parameterization (ablation) | PlaneAE · Stanford2D3D validation | Per-plane recall: 0.341 -> 0.368 | Improved |
| Add orientation grouping (ablation) | Proposed system without yaw-invariant representation · Stanford2D3D validation | Per-pixel recall: 0.545 -> 0.627 | Improved |
| Add yaw-invariant representation (ablation) | Proposed system without orientation grouping · Stanford2D3D validation | Per-plane recall: 0.417 -> 0.430 | Improved |
| Replace two binary planar classifiers with 3-way softmax classification (ablation) | H&V-planar segmentation · PanoH&V | Performance | No clear effect |
Closest papers by meaning
- PlaneRAS: Learning Planar Primitives for 3D Plane Recovery (ICCV 2025 · similarity 0.88)
- SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation (CVPR 2021 · similarity 0.88)
- PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting (NeurIPS 2025 · similarity 0.88)
- BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-Aided Adversarial Learning (ECCV 2022 · similarity 0.87)
- PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes (CVPR 2025 · similarity 0.87)
- MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction (NeurIPS 2026 · 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.
