Research map / Architectures and efficiency / Pruning and efficient tuning
Mapillary Planet-Scale Depth Dataset
Manuel López Antequera, Pau Gargallo, Markus Hofinger, Samuel Rota Bulò, Yubin Kuang, Peter Kontschieder
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 |
|---|---|---|---|
| train on MPSD instead of MegaDepth (camera normalization) | u-net depth network · KITTI | SILog: 26.79 -> 12.77 | Improved |
| train on MPSD instead of MegaDepth (camera normalization) | u-net depth network · Cityscapes | SILog: 36.73 -> 19.77 | Improved |
| train on MPSD instead of MegaDepth (camera normalization) | u-net depth network · Make3D | SILog: 41.64 -> 27.49 | Improved |
| train on MPSD instead of MegaDepth (camera normalization) | u-net depth network · MegaDepth | SILog: 9.96 -> 14.68 | Hurt |
| use full MPSD rather than size-matched mini MPSD (ablation) | u-net depth network · KITTI | SILog: 14.89 -> 12.77 | Improved |
| add camera normalization instead of naive resize when training on MegaDepth (ablation) | MegaDepth u-net · Cityscapes | SILog: 65.11 -> 36.73 | Improved |
| use CAM-Convs instead of camera normalization on MPSD | MPSD u-net · Cityscapes | SILog: 19.77 -> 34.83 | Hurt |
| use random instead of center crops with CAM-Convs on MegaDepth (ablation) | CAM-Convs MegaDepth · KITTI | SILog: 23.79 -> 26.92 | No clear effect |
| combine camera normalization with CAM-Convs on MPSD (ablation) | MPSD camera normalization · DIODE | SILog: 42.2 -> 41.69 | Improved |
| fine-tune MPSD network on KITTI | MPSD camera normalization · KITTI | SILog: 12.77 -> 9.23 | Improved |
| fine-tune MPSD network on KITTI | MPSD camera normalization · Cityscapes | SILog: 19.77 -> 27.11 | Hurt |
| pre-train on MPSD instead of MegaDepth before KITTI fine-tuning | depth network · KITTI val dynamic regions | RMSE (m): 4.29 -> 3.52 | Improved |
Closest papers by meaning
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.86)
- Depth Anything V2 (NeurIPS 2024 · similarity 0.86)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.86)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.86)
- RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions (NeurIPS 2024 · similarity 0.85)
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.85)
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.
