Research map / 3D vision / Depth and stereo
Geometric Distillation from Rectified Stereo: Leveraging Epipolar Cues for Monocular Depth
Jung-Hee Kim, Xiaoming Liu
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 EpiDistill | UniDepthV2 · DIODE | Abs Rel: 0.716 -> 0.396 | Improved |
| add EpiDistill | UniDepthV2 · KITTI | Abs Rel: 0.080 -> 0.074 | Improved |
| add EpiDistill | UniDepthV2 · ETH3D | Abs Rel: 0.176 -> 0.137 | Improved |
| add EpiDistill | DepthPro · ETH3D | Abs Rel: 0.355 -> 0.354 | No clear effect |
| add EpiDistill | DepthPro · NYU | Abs Rel: 0.098 -> 0.110 | Hurt |
| add EpiDistill | UniDepthV2 · NYU | Abs Rel: 0.077 -> 0.077 | No clear effect |
| add EpiDistill | UniDepthV2 · Booster | Abs Rel: 0.179 -> 0.171 | Improved |
| add EpiDistill | UniDepthV2 · DepthPerturb | Abs Rel: 0.241 -> 0.167 | Improved |
| add EpiDistill | DepthPro · DepthPerturb | Abs Rel: 0.248 -> 0.178 | Improved |
| use depth-guided epipolar attention instead of global attention (ablation) | UniDepthV2 · KITTI+ETH3D average | Abs Rel: 0.119 -> 0.113 | Improved |
| add rectified stereo tokens to DGEA (ablation) | UniDepthV2 · KITTI+ETH3D average | Abs Rel: 0.113 -> 0.101 | Improved |
| add DGEA and RST over plain fine-tuning (ablation) | UniDepthV2 · KITTI+ETH3D average | Abs Rel: 0.124 -> 0.101 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DepthPro — Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025) · better on 9 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models (ECCV 2026 · similarity 0.91)
- 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)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.89)
- SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation (CVPR 2025 · similarity 0.89)
- UniDepth: Universal Monocular Metric Depth Estimation (CVPR 2024 · 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.
