Research map / 3D vision / Depth and stereo
Joint Graph-Based Depth Refinement and Normal Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 graph-based piece-wise planar regularization instead of NLTGV (ablation) | SGM disparity refinement · Middlebury v3 training | bad 2px: 19.88 -> 19.25 | Helped |
| Use graph-based piece-wise planar regularization instead of NLTGV (ablation) | BM disparity refinement · Middlebury v3 training | bad 2px: 22.03 -> 19.41 | Helped |
| Refine SGM disparity with the proposed method | SGM · KITTI 2015 training | bad 3px: 10.11 -> 5.54 | Helped |
| Use graph-based piece-wise planar regularization instead of NLTGV (ablation) | SGM disparity refinement · KITTI 2015 training | bad 3px: 6.07 -> 5.54 | Helped |
| Use graph-based piece-wise planar regularization instead of NLTGV (ablation) | BM disparity refinement · KITTI 2015 training | bad 3px: 6.76 -> 6.40 | Helped |
| Refine MVS depth with the proposed method | PatchMatch MVS · ETH3D training average | 2cm error percentage: 29.95 -> 22.54 | Helped |
| Use graph-based piece-wise planar regularization instead of the reported prior refinement method | PatchMatch MVS · ETH3D training average | avgerr: 0.109 -> 0.091 | Helped |
| Use graph-based piece-wise planar regularization instead of NLTGV (ablation) | Depth refinement · Middlebury, KITTI, and ETH3D | depth error | Helped |
Closest papers by meaning
- P3Depth: Monocular Depth Estimation With a Piecewise Planarity Prior (CVPR 2022 · similarity 0.89)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
- PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting (NeurIPS 2025 · similarity 0.87)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection (NeurIPS 2026 · similarity 0.87)
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation (CVPR 2025 · 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.