Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression
Dongting Hu, Liuhua Peng, Tingjin Chu, Xiaoxing Zhang, Yinian Mao, Howard Bondell, Mingming Gong
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 estimation variance to error variance (predictive variance) (ablation) | ConOR+WBS · KITTI (Eigen split) | AUSE (rmse): 0.097 -> 0.095 | Improved |
| add estimation variance to error variance (predictive variance) (ablation) | ConOR+WBS · NYUv2 | AUSE (rmse): 0.305 -> 0.297 | Improved |
| use constrained ordinal regression instead of unconstrained OR (ablation) | ConOR · KITTI (Eigen split) | AUSE (rmse): 0.108 -> 0.097 | Improved |
| use constrained ordinal regression instead of unconstrained OR (ablation) | ConOR · KITTI (Eigen split) | depth rmse: 2.766 -> 2.709 | Improved |
| use constrained ordinal regression instead of unconstrained OR (ablation) | ConOR · NYUv2 | AUSE (rmse): 0.314 -> 0.305 | Improved |
| add MC dropout for estimation variance (ablation) | ConOR · KITTI (Eigen split) | AUSE (rmse): 0.097 -> 0.104 | Hurt |
| add deep ensemble for estimation variance (ablation) | ConOR · KITTI (Eigen split) | AUSE (rmse): 0.097 -> 0.096 | No clear effect |
| add multiplier bootstrap for estimation variance (ablation) | ConOR · KITTI (Eigen split) | AUSE (rmse): 0.097 -> 0.094 | Improved |
| add wild bootstrap for estimation variance (ablation) | ConOR · NYUv2 | AUSE (rmse): 0.305 -> 0.297 | Improved |
| add MC dropout for estimation variance (ablation) | ConOR · NYUv2 | AUSE (rmse): 0.305 -> 0.305 | No clear effect |
| use spacing-increasing discretization instead of uniform (ablation) | ConOR · KITTI (Eigen split) | rmse and uncertainty | Improved |
| increase number of bins (ablation) | ConOR · KITTI (Eigen split) | uncertainty estimation: rmse stays between 2.7 and 2.8 | Improved |
Closest papers by meaning
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.87)
- Scalable Autoregressive Monocular Depth Estimation (CVPR 2025 · similarity 0.87)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.87)
- Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations (NeurIPS 2025 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.86)
- MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction (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.
