Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2207.14466 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910535516160000 |
|---|---|
| author | Xu, Guangkai Yin, Wei Zhang, Jianming Wang, Oliver Niklaus, Simon Chen, Simon Bian, Jia-Wang |
| author_facet | Xu, Guangkai Yin, Wei Zhang, Jianming Wang, Oliver Niklaus, Simon Chen, Simon Bian, Jia-Wang |
| contents | Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by various range sensors, including those in modern mobile phones, or by multi-view reconstruction algorithms. Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model. We propose an effective training scheme where we simulate various sparsity patterns in typical task domains. In addition, we design two new benchmarks to evaluate the generalizability and the robustness of depth completion methods. Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods, introducing a practical solution to high-quality depth capture on a mobile device. The code is available at: https://github.com/YvanYin/FillDepth. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_14466 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Towards Domain-agnostic Depth Completion Xu, Guangkai Yin, Wei Zhang, Jianming Wang, Oliver Niklaus, Simon Chen, Simon Bian, Jia-Wang Computer Vision and Pattern Recognition Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by various range sensors, including those in modern mobile phones, or by multi-view reconstruction algorithms. Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model. We propose an effective training scheme where we simulate various sparsity patterns in typical task domains. In addition, we design two new benchmarks to evaluate the generalizability and the robustness of depth completion methods. Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods, introducing a practical solution to high-quality depth capture on a mobile device. The code is available at: https://github.com/YvanYin/FillDepth. |
| title | Towards Domain-agnostic Depth Completion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2207.14466 |