Research map / 3D vision / Depth and stereo
TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrast
Beilei Cui, Yiming Huang, Long Bai, Hongliang Ren
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 pixel-wise rescale maps instead of two single factors (ablation) | TR2M · iBims-1 (zero-shot) | delta1: 0.566 -> 0.657 | Improved |
| add pixel-wise rescale maps instead of two single factors (ablation) | TR2M · NYUv2 | Abs Rel: 0.118 -> 0.084 | Improved |
| add threshold pseudo metric depth supervision L_tp-si (ablation) | TR2M · NYUv2 | Abs Rel: 0.084 -> 0.085 | No clear effect |
| add threshold pseudo metric depth supervision L_tp-si (ablation) | TR2M · iBims-1 (zero-shot) | delta1: 0.657 -> 0.708 | Improved |
| add threshold pseudo metric depth supervision L_tp-si (ablation) | TR2M · DIODE Outdoor (zero-shot) | delta1: 0.237 -> 0.243 | Improved |
| add dual-level scale-oriented contrast L_soc (ablation) | TR2M · iBims-1 (zero-shot) | delta1: 0.708 -> 0.736 | Improved |
| add dual-level scale-oriented contrast L_soc (ablation) | TR2M · DIODE Outdoor (zero-shot) | delta1: 0.243 -> 0.274 | Improved |
| add image input to text-only model (ablation) | TR2M · NYUv2 | Abs Rel: 0.114 -> 0.082 | Improved |
| add text input to image-only model (ablation) | TR2M · iBims-1 (zero-shot) | delta1: 0.704 -> 0.736 | Improved |
| add text input to image-only model (ablation) | TR2M · NYUv2 | Abs Rel: 0.085 -> 0.082 | Improved |
| train DepthAnything on mixed datasets (DA Mix) instead of single-domain models | DA · iBims-1 (zero-shot) | Abs Rel: 0.150 -> 0.158 | Hurt |
| pixel-wise rescale maps instead of global rescale factors (TR2M vs RSA) | relative-to-metric transfer · KITTI | delta1: 0.786 -> 0.965 | Improved |
Closest papers by meaning
- RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions (NeurIPS 2024 · similarity 0.91)
- SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation (CVPR 2025 · similarity 0.90)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.89)
- DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images (NeurIPS 2026 · similarity 0.89)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.89)
- UniDepth: Universal Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.89)
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.
