Research map / 3D vision / Depth and stereo
Monocular Depth Estimation Using Relative Depth Maps
Jae-Han Lee, Chang-Su Kim
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 |
|---|---|---|---|
| estimate and combine relative depth maps with ordinary depth maps (ablation) | Proposed monocular depth estimation method · NYUv2 test | Spearman's ρ: 0.885 -> 0.914 | Improved |
| add relative depth maps R3, R4, R5, and R6 to D3 (ablation) | Proposed method · NYUv2 test | RMSE (lin): 0.583 -> 0.538 | Improved |
| add relative depth maps R3, R4, R5, and R6 to D3 (ablation) | Proposed method · NYUv2 test | ARD: 0.143 -> 0.131 | Improved |
| use a higher-resolution ordinary depth map instead of D3 alone (ablation) | Ordinary-depth-only variant · NYUv2 test | RMSE (lin): 0.583 -> 0.552 | Improved |
| add ordinary depth maps D4 through D7 to D3 and R3 through R7 (ablation) | Proposed method · NYUv2 test | Spearman's ρ: 0.914 -> 0.912 | Hurt |
| add R7 to D3, R3, R4, R5, and R6 (ablation) | Proposed method · NYUv2 test | RMSE (lin): 0.538 -> 0.538 | No clear effect |
| add relative depth maps to D3 (ablation) | Proposed method · NYUv2 test | RMSE (lin): 0.550 -> 0.538 | Improved |
Closest papers by meaning
- Depth Map Decomposition for Monocular Depth Estimation (ECCV 2022 · similarity 0.91)
- Visualization of Convolutional Neural Networks for Monocular Depth Estimation (ICCV 2019 · similarity 0.89)
- Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions (NeurIPS 2016 · similarity 0.89)
- Semi-Supervised Adversarial Monocular Depth Estimation (TPAMI 2019 · similarity 0.89)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.88)
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.
