Single Image Depth Estimation with Normal Guided Scale Invariant Deep Convolutional Fields
Estimating scene depth from a single image can be widely applied to understand 3D environments due to the easy access of the images captured by consumer-level cameras. Previous works exploit Conditional Random Fields (CRF) to estimate image depth, where neighboring pixels (superpixels) with similar appearance are constrained to share the same depth. However, the depth may vary significantly in the slanted surface, thus leading to severe estimation errors. In order to eliminate those errors, we propose a superpixel based normal guided scale invariant deep convolutional field by encouraging the neighboring superpixels with similar appearance to lie on the same 3D plane of the scene. In doing so, a depth-normal multitask CNN is introduced to produce the superpixel-wise depth and surface normal predictions simultaneously. To correct the errors of the roughly estimated superpiexl-wise depth, we develop a normal guided scale invariant CRF (NGSI-CRF). NGSI-CRF consists of a scale invariant unary potential which is able to measure the relative depth between superpixels as well as the absolute depth of superpixels, and a normal guided pairwise potential which constrains spatial relationships between superpixels in accordance with the 3D layout of the scene. In other words, the normal guided pairwise potential is designed to smooth the depth prediction without deteriorating the 3D structure of the depth prediction. The superpixel-wise depth maps estimated by NGSI-CRF will be fed into a pixel-wise refinement module to produce a smooth fine-grained depth prediction. Furthermore, we derive a closed form solution for the maximum a posteriori (MAP) inference of NGSI-CRF. Thus, our proposed network can be efficiently trained in an end-to-end manner. We conduct our experiments on various datasets, such as NYU-D2, KITTI and Make3D. As demonstrated in the experimental results, our method achieves superior performance in both indoor and outdoor scenes.
- System : Pentium Dual Core.
- Hard Disk : 120 GB.
- Monitor : 15’’ LED
- Input Devices : Keyboard, Mouse
- Ram :1 GB
- Operating system : Windows 7.
- Coding Language :
- Tool : MATLAB R2013A /2018
Han Yan, Xin Yu, Yu Zhang, Shunli Zhang, Xiaolin Zhao, and Li Zhang, “Single Image Depth Estimation with Normal Guided Scale Invariant Deep Convolutional Fields”, IEEE 2019.