Research map / Label-efficient and robust learning / Recognition and long-tail
IEBins: Iterative Elastic Bins for Monocular Depth Estimation
Shuwei Shao, Zhongcai Pei, Xingming Wu, Zhong Liu, Weihai Chen, Zhengguo Li
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 |
|---|---|---|---|
| use iterative elastic bins instead of the strongest listed baseline | IEBins with Swin-Large · KITTI Eigen split | Abs Rel: 0.051 -> 0.050 | Improved |
| use IEBins instead of the strongest listed baseline | IEBins · KITTI official test | SILog: 10.14 -> 9.63 | Improved |
| use IEBins instead of the strongest listed baseline | IEBins with Swin-Large · NYU-Depth-v2 | Abs Rel: 0.090 -> 0.087 | Improved |
| use IEBins instead of the strongest listed baseline | IEBins with Swin-Large · SUN RGB-D zero-shot | Abs Rel: 0.143 -> 0.135 | Improved |
| add elastic target bins to iterative bin refinement (ablation) | Baseline + IBins · NYU-Depth-v2 | Abs Rel: 0.090 -> 0.087 | Improved |
| replace standard regression with iterative elastic bins (ablation) | Baseline + Regression · NYU-Depth-v2 | Abs Rel: 0.095 -> 0.087 | Improved |
| use 4 bins instead of 16 (ablation) | IEBins · NYU-Depth-v2 | Abs Rel: 0.087 -> 0.105 | Hurt |
| use 8 bins instead of 16 (ablation) | IEBins · NYU-Depth-v2 | Abs Rel: 0.087 -> 0.089 | Hurt |
| use 32 bins instead of 16 (ablation) | IEBins · NYU-Depth-v2 | Abs Rel: 0.087 -> 0.088 | No clear effect |
| use 4 bins instead of 16 (ablation) | IEBins · KITTI Eigen split | Abs Rel: 0.050 -> 0.288 | Hurt |
| use 8 bins instead of 16 (ablation) | IEBins · KITTI Eigen split | Abs Rel: 0.050 -> 0.054 | Hurt |
| use 32 bins instead of 16 (ablation) | IEBins · KITTI Eigen split | Abs Rel: 0.050 -> 0.050 | No clear effect |
Closest papers by meaning
- IEBins: Iterative Elastic Bins for Monocular Depth Estimation and Completion (IJCV 2024 · similarity 0.91)
- MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation (CVPR 2026 · similarity 0.86)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.86)
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.85)
- UniDepth: Universal 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.
