Research map / 3D vision / Depth and stereo
Globally Optimal Vertical Direction Estimation in Atlanta World
Yinlong Liu, Guang Chen, Alois Knoll
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 |
|---|---|---|---|
| search vertical direction on S^2 instead of rotation search in SO(3) | BnB vertical direction estimation · Synthetic Atlanta world | runtime | Improved |
| use exp-BnB or ste-circle-BnB bounds instead of ste-square or SCS bounds (ablation) | BnB vertical direction estimation · Synthetic Atlanta world | runtime | Improved |
| use tighter ste-square or SCS bounds instead of exp or ste-circle bounds (ablation) | BnB vertical direction estimation · Synthetic Atlanta world | iterations | Improved |
| use ste-square bounds instead of exp bounds (ablation) | BnB vertical direction estimation · NYUv2 | median runtime (s): 0.134 -> 4.256 | Hurt |
| use ste-square bounds instead of exp bounds (ablation) | BnB vertical direction estimation · NYUv2 | median iterations: 816 -> 478 | Improved |
| use ste-square bounds instead of ste-circle bounds (ablation) | BnB vertical direction estimation · Outdoor Bremen | median runtime (s): 1.182 -> 88.470 | Hurt |
| use SCS parametrization instead of stereographic square parametrization (ablation) | BnB vertical direction estimation · Outdoor Bremen | median runtime (s): 88.470 -> 153.356 | Hurt |
| increase RANSAC outlier proportion assumption from 0.65 to 0.95 (ablation) | RANSAC · NYUv2 | median runtime (s): 0.007 -> 0.344 | Hurt |
| use sequential vertical-then-horizontal estimation instead of rotation search | Manhattan frame estimation · Synthetic Manhattan world | accuracy at large noise | Hurt |
| use sequential vertical-then-horizontal estimation instead of rotation search | Manhattan frame estimation · Synthetic Manhattan world | runtime | Improved |
| use exp-BnB instead of other S^2 bounds under high outlier ratio (ablation) | BnB vertical direction estimation · Synthetic high outlier / large noise | runtime | Improved |
Closest papers by meaning
- Globally Optimal Inlier Set Maximization for Atlanta World Understanding (TPAMI 2019 · similarity 0.93)
- Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation (CVPR 2018 · similarity 0.93)
- AtlantaNet: Inferring the 3D Indoor Layout from a Single 360(∘) Image beyond the Manhattan World Assumption (ECCV 2020 · similarity 0.87)
- Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World (CVPR 2025 · similarity 0.83)
- AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians (NeurIPS 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.
