Research map / Label-efficient and robust learning / Recognition and long-tail
Robust Depth Completion with Uncertainty-Driven Loss Functions
Yufan Zhu, Weisheng Dong, Leida Li, Jinjian Wu, Xin Li, Guangming Shi
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 uncertainty-driven loss with Jeffrey's prior and residual refinement | Depth completion model · KITTI Depth Completion Test | MAE: 199.59 -> 190.88 | Improved |
| Use uncertainty-driven loss with Jeffrey's prior and residual refinement | Depth completion model · KITTI Depth Completion Test | IMAE: 0.84 -> 0.83 | Improved |
| Use uncertainty-driven loss with Jeffrey's prior and residual refinement | Depth completion model · KITTI Depth Completion Test | IRMSE: 1.99 -> 1.98 | Improved |
| Use uncertainty-driven loss with Jeffrey's prior and residual refinement | Depth completion model · KITTI Depth Completion Test | RMSE: 741.68 -> 795.43 | Hurt |
| Add uncertainty-driven loss (ablation) | Depth completion model · KITTI Depth Completion Val | MAE: 211.01 -> 203.94 | Improved |
| Add uncertainty-driven loss (ablation) | Depth completion model · KITTI Depth Completion Val | RMSE: 792.34 -> 791.13 | No clear effect |
| Add Jeffrey's prior to uncertainty-driven loss (ablation) | Depth completion model · KITTI Depth Completion Val | RMSE: 791.13 -> 783.87 | Improved |
| Add residual learning (ablation) | Uncertainty-driven depth completion model · KITTI Depth Completion Val | MAE: 204.61 -> 186.90 | Improved |
| Add residual learning (ablation) | Uncertainty-driven depth completion model · KITTI Depth Completion Val | RMSE: 783.87 -> 833.67 | Hurt |
| Use 4 completion blocks rather than 1 (ablation) | Multiscale Joint Prediction Model · KITTI Depth Completion Val | MAE: 215.06 -> 204.61 | Improved |
| Use 4 completion blocks rather than 2 (ablation) | Multiscale Joint Prediction Model · KITTI Depth Completion Val | MAE: 205.95 -> 204.61 | Improved |
| Use 4 completion blocks rather than 3 (ablation) | Multiscale Joint Prediction Model · KITTI Depth Completion Val | MAE: 206.46 -> 204.61 | Improved |
Closest papers by meaning
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.91)
- Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data (IJCV 2022 · similarity 0.90)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.87)
- Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior (AAAI 2025 · similarity 0.87)
- Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement (CVPR 2024 · similarity 0.86)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular 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.
