BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models?
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_ | 1866913950438785024 |
|---|---|
| author | Li, Zhenyu Lin, Haotong Feng, Jiashi Wonka, Peter Kang, Bingyi |
| author_facet | Li, Zhenyu Lin, Haotong Feng, Jiashi Wonka, Peter Kang, Bingyi |
| contents | Depth estimation is a fundamental task in computer vision with diverse applications. Recent advancements in deep learning have led to powerful depth foundation models (DFMs), yet their evaluation remains challenging due to inconsistencies in existing protocols. Traditional benchmarks rely on alignment-based metrics that introduce biases, favor certain depth representations, and complicate fair comparisons. In this work, we propose BenchDepth, a new benchmark that evaluates DFMs through five carefully selected downstream proxy tasks: depth completion, stereo matching, monocular feed-forward 3D scene reconstruction, SLAM, and vision-language spatial understanding. Unlike conventional evaluation protocols, our approach assesses DFMs based on their practical utility in real-world applications, bypassing problematic alignment procedures. We benchmark eight state-of-the-art DFMs and provide an in-depth analysis of key findings and observations. We hope our work sparks further discussion in the community on best practices for depth model evaluation and paves the way for future research and advancements in depth estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15321 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models? Li, Zhenyu Lin, Haotong Feng, Jiashi Wonka, Peter Kang, Bingyi Computer Vision and Pattern Recognition Depth estimation is a fundamental task in computer vision with diverse applications. Recent advancements in deep learning have led to powerful depth foundation models (DFMs), yet their evaluation remains challenging due to inconsistencies in existing protocols. Traditional benchmarks rely on alignment-based metrics that introduce biases, favor certain depth representations, and complicate fair comparisons. In this work, we propose BenchDepth, a new benchmark that evaluates DFMs through five carefully selected downstream proxy tasks: depth completion, stereo matching, monocular feed-forward 3D scene reconstruction, SLAM, and vision-language spatial understanding. Unlike conventional evaluation protocols, our approach assesses DFMs based on their practical utility in real-world applications, bypassing problematic alignment procedures. We benchmark eight state-of-the-art DFMs and provide an in-depth analysis of key findings and observations. We hope our work sparks further discussion in the community on best practices for depth model evaluation and paves the way for future research and advancements in depth estimation. |
| title | BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.15321 |