تقرير
Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
| العنوان: | Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging |
|---|---|
| المؤلفون: | Miangoleh, S. Mahdi H., Dille, Sebastian, Mai, Long, Paris, Sylvain, Aksoy, Yağız |
| المصدر: | Proc. CVPR (2021) |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method builds on our analysis on how the input resolution and the scene structure affects depth estimation performance. We demonstrate that there is a trade-off between a consistent scene structure and the high-frequency details, and merge low- and high-resolution estimations to take advantage of this duality using a simple depth merging network. We present a double estimation method that improves the whole-image depth estimation and a patch selection method that adds local details to the final result. We demonstrate that by merging estimations at different resolutions with changing context, we can generate multi-megapixel depth maps with a high level of detail using a pre-trained model. Comment: For more details visit http://yaksoy.github.io/highresdepth/ |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2105.14021 |
| رقم الأكسشن: | edsarx.2105.14021 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |