Research map / 3D vision / Depth and stereo
One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images
Byeongjun Kwon, Munchurl 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 Bias Free Masking (BFM) (ablation) | PRO baseline (a) · Booster | AbsRel: 0.0385 -> 0.0303 | Improved |
| add BFM (ablation) | PRO baseline (a) · NuScenes | AbsRel: 0.105 -> 0.105 | No clear effect |
| add GPCT (ablation) | PRO baseline (a) · Consistency Error | CE: 0.208 -> 0.058 | Improved |
| add BFM (ablation) | PRO baseline (a) · Consistency Error | CE: 0.208 -> 0.117 | Improved |
| add BFM on top of GPCT (ablation) | PRO · Booster | AbsRel: 0.0313 -> 0.0304 | Improved |
| add BFM on top of GPCT (ablation) | PRO · Middlebury 2014 | D3R: 0.0792 -> 0.0803 | Hurt |
| increase GPCT overlap from 28 to 224 pixels (ablation) | PRO · ETH3D | CE: 0.108 -> 0.049 | Improved |
| increase GPCT overlap from 224 to 448 pixels (ablation) | PRO · ETH3D | CE: 0.049 -> 0.060 | Hurt |
| use GPCT instead of diagonal consistency (ablation) | PRO · Consistency Error | CE: 0.075 -> 0.049 | Improved |
| replace Conv block by Frequency Fusion Module (ablation) | PRO · DIS-5K | BR: 0.127 -> 0.156 | Improved |
| replace Conv block by Frequency Fusion Module (ablation) | PRO · UHRSD | BR: 0.071 -> 0.083 | Improved |
| increase inference patch grid from 3x3 to 5x5 (ablation) | PRO · DIS-5K | BR: 0.125 -> 0.162 | Improved |
Closest papers by meaning
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.91)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.89)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.89)
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (CVPR 2025 · similarity 0.88)
- FoundationStereo: Zero-Shot Stereo Matching (CVPR 2025 · similarity 0.88)
- DepthFM: Fast Generative Monocular Depth Estimation with Flow Matching (AAAI 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.
