Research map / Detection and segmentation / CNN features
Pixel-wise Planarity for High-Precision Monocular Plane Segmentation
Ahmetcan Yavuz, Alpay Ozkan, Rémi Pautrat, Shaohui Liu, Marc Pollefeys
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 relative depth cue to normal cue in region growing (ablation) | region growing · ScanNet++ | precision @0.1cm: 43.0 -> 45.5 | Improved |
| add predicted planarity map as third gating cue (ablation) | region growing · ScanNet++ | precision @0.1cm: 45.5 -> 62.1 | Improved |
| add predicted planarity gating (recall cost) (ablation) | region growing · ScanNet++ | recall @0.5cm: 64.2 -> 60.1 | Hurt |
| use depth cue alone instead of normals (ablation) | region growing · ScanNet++ | precision @0.1cm: 0.6 vs 43.0 | Hurt |
| source normals and depth from different pretrained models instead of MoGeV2 (ablation) | pipeline · ScanNet++ | precision @0.1cm: 62.1 -> 27.3 | Hurt |
| replace MoGeV2 normals and depth with Metric3D (ablation) | pipeline · ScanNet++ | precision @0.1cm: 62.1 -> 21.0 | Hurt |
| use Focal loss instead of BCE for planarity head (ablation) | planarity head · ScanNet++ | precision @0.1cm: 62.1 -> 57.9 | Mixed |
| use Dice loss instead of BCE for planarity head (ablation) | planarity head · ScanNet++ | precision @0.1cm: 62.1 -> 62.3 | No clear effect |
| use shallow conv probe instead of standalone planarity head (ablation) | planarity head · ScanNet++ | precision @0.1cm: 62.1 -> 69.0 | Mixed |
| retrain ZeroPlane on our GT with same backbone | Zeroplane · ScanNet++ | precision @0.1cm: 16.6 vs 62.1 | Hurt |
| tighten region-growing thresholds (default to strict) (ablation) | region growing · ScanNet++ | precision @0.1cm / recall: 68.0 -> 81.9; recall 42.3 -> 32.3 | Mixed |
| use planarity-guided method instead of Zeroplane on out-of-domain outdoor data | Ours · VKITTI2 (trained indoors) | precision @2cm: 22.5 -> 62.1 | Improved |
Closest papers by meaning
- P3Depth: Monocular Depth Estimation With a Piecewise Planarity Prior (CVPR 2022 · similarity 0.87)
- PlaneRAS: Learning Planar Primitives for 3D Plane Recovery (ICCV 2025 · similarity 0.85)
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation (CVPR 2025 · similarity 0.84)
- AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos (NeurIPS 2024 · similarity 0.84)
- AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings (CVPR 2024 · similarity 0.83)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (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.
