Research map / 3D vision / Depth and stereo
Depth Map Decomposition for Monocular Depth Estimation
Jinyoung Jun, Jae-Han Lee, Chul Lee, Chang-Su 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 N-Net decoder to metric-only network (ablation) | M-Net baseline · NYUv2 (17K) | RMSE: 0.400 -> 0.389 | Improved |
| add G-Net gradient decoder (ablation) | M+N network · NYUv2 (17K) | RMSE: 0.389 -> 0.387 | Improved |
| add MDR block with mean prediction deactivated (ablation) | M+N+G network · NYUv2 (17K) | RMSE: 0.387 -> 0.381 | Improved |
| activate mean prediction in the MDR block (ablation) | MDR* network · NYUv2 (17K) | RMSE: 0.381 -> 0.370 | Improved |
| add HR-WSI relative-depth data (ablation) | Proposed · NYUv2 (17K) | RMSE: 0.370 -> 0.362 | Improved |
| use two-phase training instead of single-phase (ablation) | Proposed · NYUv2 (17K) | RMSE: 0.386 -> 0.362 | Improved |
| add G-Net, N-Net and MDR over bare encoder-decoder | Baseline · NYUv2 (795) | RMSE: 0.487 -> 0.468 | Improved |
| add HR-WSI relative depth data | Proposed · NYUv2 (795) | RMSE: 0.468 -> 0.417 | Improved |
| add G-Net, N-Net and MDR over bare encoder-decoder | Baseline · DIML-Indoor | RMSE: 0.589 -> 0.537 | Improved |
| add HR-WSI relative depth data | Proposed · DIML-Indoor | RMSE: 0.537 -> 0.517 | Improved |
| add G-Net, N-Net and MDR over bare encoder-decoder | Baseline · SUN RGB-D | RMSE: 0.306 -> 0.303 | Improved |
| add HR-WSI relative depth data | Proposed · SUN RGB-D | RMSE: 0.303 -> 0.301 | Improved |
Closest papers by meaning
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.89)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.89)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
- RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions (NeurIPS 2024 · similarity 0.88)
- SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation (CVPR 2025 · similarity 0.87)
- UniDepth: Universal Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.87)
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.
