Research map / Learning theory and algorithms / Combinatorial and search optimization
Globally Optimal Manhattan Frame Estimation in Real-Time
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
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 |
|---|---|---|---|
| Replace exhaustive per-normal bound evaluation with rectangular EGI bounds and an integral image | Branch-and-bound Manhattan Frame estimation · NYUv2 ground truth benchmark | runtime: 117.06 -> 0.07 | Improved |
| Relax the inlier constraint to axis-aligned rectangular EGI bounds | Branch-and-bound Manhattan Frame estimation · NYUv2 ground truth benchmark | average angular error: 2.5° -> 2.63° | Hurt |
| Increase the EGI resolution parameter (ablation) | Proposed BnB · Synthetic simulation | angular error | Improved |
| Increase the EGI resolution parameter (ablation) | Proposed BnB · Synthetic simulation | runtime | Hurt |
| Vary the inlier threshold (ablation) | Proposed BnB · Synthetic simulation | angular error | No clear effect |
| Increase noise variance (ablation) | Proposed BnB · Synthetic vMF-distributed surface normals | angular error | No clear effect |
| Use the proposed method instead of RMFE as noise variance changes | Synthetic vMF-distributed surface normals · Synthetic simulation | angular error | Improved |
Closest papers by meaning
- Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time (TPAMI 2018 · similarity 0.97)
- Globally Optimal and Efficient Manhattan Frame Estimation by Delimiting Rotation Search Space (ICCV 2021 · similarity 0.91)
- The Manhattan Frame Model—Manhattan World Inference in the Space of Surface Normals (TPAMI 2017 · similarity 0.89)
- Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor (NeurIPS 2024 · similarity 0.83)
- Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World (CVPR 2025 · similarity 0.82)
- Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption (CVPR 2024 · similarity 0.82)
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.
