A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909456515727360 |
|---|---|
| author | Landgraf, Steven Qin, Rongjun Ulrich, Markus |
| author_facet | Landgraf, Steven Qin, Rongjun Ulrich, Markus |
| contents | While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting absolute distances, poses particular challenges, as even the most advanced foundation models remain prone to critical errors. Since quantifying the uncertainty has emerged as a promising endeavor to address these limitations and enable trustworthy deployment, we fuse five different uncertainty quantification methods with the current state-of-the-art DepthAnythingV2 foundation model. To cover a wide range of metric depth domains, we evaluate their performance on four diverse datasets. Our findings identify fine-tuning with the Gaussian Negative Log-Likelihood Loss (GNLL) as a particularly promising approach, offering reliable uncertainty estimates while maintaining predictive performance and computational efficiency on par with the baseline, encompassing both training and inference time. By fusing uncertainty quantification and foundation models within the context of monocular depth estimation, this paper lays a critical foundation for future research aimed at improving not only model performance but also its explainability. Extending this critical synthesis of uncertainty quantification and foundation models into other crucial tasks, such as semantic segmentation and pose estimation, presents exciting opportunities for safer and more reliable machine vision systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation Landgraf, Steven Qin, Rongjun Ulrich, Markus Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting absolute distances, poses particular challenges, as even the most advanced foundation models remain prone to critical errors. Since quantifying the uncertainty has emerged as a promising endeavor to address these limitations and enable trustworthy deployment, we fuse five different uncertainty quantification methods with the current state-of-the-art DepthAnythingV2 foundation model. To cover a wide range of metric depth domains, we evaluate their performance on four diverse datasets. Our findings identify fine-tuning with the Gaussian Negative Log-Likelihood Loss (GNLL) as a particularly promising approach, offering reliable uncertainty estimates while maintaining predictive performance and computational efficiency on par with the baseline, encompassing both training and inference time. By fusing uncertainty quantification and foundation models within the context of monocular depth estimation, this paper lays a critical foundation for future research aimed at improving not only model performance but also its explainability. Extending this critical synthesis of uncertainty quantification and foundation models into other crucial tasks, such as semantic segmentation and pose estimation, presents exciting opportunities for safer and more reliable machine vision systems. |
| title | A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.08188 |