Research map / 3D vision / Depth and stereo
LDL: Line Distance Functions for Panoramic Localization
Junho Kim, Changwoon Choi, Hojun Jang, Young Min Kim
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 |
|---|---|---|---|
| add distance function decomposition along principal directions (ablation) | LDL · OmniScenes Extreme | accuracy: 0.37 -> 0.92 | Improved |
| use 42 query points instead of 10 (ablation) | LDL · OmniScenes Extreme | accuracy: 0.77 -> 0.92 | Improved |
| increase query points from 42 to 84 (ablation) | LDL · OmniScenes Extreme | accuracy: 0.92 -> 0.95 | Mixed |
| use inlier-counting robust loss instead of L1/L2/Huber/Median (ablation) | LDL · OmniScenes Wedding Hall | accuracy: 0.55 -> 0.68 | Improved |
| sample query points uniformly on sphere instead of along lines (ablation) | LDL · Stanford 2D-3D-S (Total) | accuracy: 0.66 -> 0.83 | Improved |
| use noisier SfM line maps instead of 3D scan lines (ablation) | LDL · OmniScenes Rooms 3,5 | accuracy: 0.98 -> 0.85 | Hurt |
| line-based feature filtering for privacy (ablation) | LDL refinement · Stanford 2D-3D-S (Total) | accuracy: 0.83 -> 0.77 | Hurt |
| use line distance functions under synthetic illumination changes | LDL vs CPO · OmniScenes Room 3 Extreme (gamma) | accuracy: 0.00 -> 0.82 | Improved |
| line distance functions in place of Chamfer distance | line-based pose selection · Stanford 2D-3D-S (Total) | accuracy: 0.39 -> 0.83 | Improved |
| LDL vs structure-based (NetVLAD) on clean Stanford data | LDL · Stanford 2D-3D-S (Total) | accuracy: 0.85 -> 0.83 | No clear effect |
| run pose search on GPU instead of CPU | LDL · OmniScenes runtime | total runtime (sec): 6.890 -> 0.738 | Improved |
Closest papers by meaning
- Fully Geometric Panoramic Localization (CVPR 2024 · similarity 0.92)
- Interacted Planes Reveal 3D Line Mapping (TPAMI 2026 · similarity 0.85)
- Pano360: Perspective to Panoramic Vision with Geometric Consistency (CVPR 2026 · similarity 0.85)
- Unified Panoramic Geometry Estimation via Multi-View Foundation Models (NeurIPS 2026 · similarity 0.84)
- GPVK-VL: Geometry-Preserving Virtual Keyframes for Visual Localization under Large Viewpoint Changes (CVPR 2025 · similarity 0.84)
- Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images (CVPR 2025 · similarity 0.83)
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.
