Research map / Label-efficient and robust learning / Domain adaptation and generalization
AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation
Read the paperCheck 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 |
|---|---|---|---|
| Adapt the synthetic-trained model using adversarial learning and feature consistency regularization | AdaDepth-U · NYU Depth Test Set | rms: 1.094 -> 0.603 | Helped |
| Adapt the synthetic-trained model using adversarial learning and feature consistency regularization | AdaDepth-U · Eigen Test Split of KITTI | rms: 8.245 -> 7.157 | Helped |
| Use domain consistency regularization (ablation) | AdaDepth adaptation · NYU Depth Test Set | rms: 1.094 -> 0.669 | Helped |
| Use residual transfer framework (ablation) | AdaDepth adaptation · NYU Depth Test Set | rms: 0.669 -> 0.658 | Helped |
| Use feature consistency framework (ablation) | AdaDepth adaptation · NYU Depth Test Set | rms: 0.658 -> 0.603 | Helped |
| Remove the depth discriminator DY (ablation) | AdaDepth-FCF · NYU Depth Test Set | rms: 0.603 -> 0.662 | Hurt |
| Use domain consistency regularization (ablation) | AdaDepth adaptation · Eigen Test Split of KITTI | rms: 8.245 -> 8.095 | Helped |
| Use residual transfer framework (ablation) | AdaDepth adaptation · Eigen Test Split of KITTI | rms: 8.095 -> 7.832 | Helped |
| Use feature consistency framework (ablation) | AdaDepth adaptation · Eigen Test Split of KITTI | rms: 7.832 -> 7.157 | Helped |
| Add a small set of labeled target samples to unsupervised adaptation | AdaDepth-U · NYU Depth v2 Test Dataset | rms: 0.603 -> 0.506 | Helped |
| Add a small set of labeled target samples to unsupervised adaptation | AdaDepth-U · Eigen Test Split of KITTI | rms: 7.157 -> 5.578 | Helped |
| Add a small set of labeled target samples to unsupervised adaptation | AdaDepth-U · Make3D Test Set | rms: 11.567 -> 9.559 | Helped |
Closest papers by meaning
- Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation (CVPR 2019 · similarity 0.90)
- Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer (CVPR 2018 · similarity 0.89)
- DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain (NeurIPS 2024 · similarity 0.88)
- UniDepth: Universal Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.87)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.86)
- SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation (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.