GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
| Autor: | Renjie Liao, Xiaojuan Qi, Zhengzhe Liu, Jiaya Jia, Raquel Urtasun |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry 020207 software engineering 02 engineering and technology Residual Kernel (image processing) Depth map Normal mapping 0202 electrical engineering electronic engineering information engineering Surface roughness Kernel regression 020201 artificial intelligence & image processing Artificial intelligence business Algorithm Normal |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2018.00037 |
| Popis: | In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image. Building on top of two-stream CNNs, our GeoNet incorporates geometric relation between depth and surface normal via the new depth-to-normal and normal-to-depth networks. Depth-to-normal network exploits the least square solution of surface normal from depth and improves its quality with a residual module. Normal-to-depth network, contrarily, refines the depth map based on the constraints from the surface normal through a kernel regression module, which has no parameter to learn. These two networks enforce the underlying model to efficiently predict depth and surface normal for high consistency and corresponding accuracy. Our experiments on NYU v2 dataset verify that our GeoNet is able to predict geometrically consistent depth and normal maps. It achieves top performance on surface normal estimation and is on par with state-of-the-art depth estimation methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|