View source for Neural RGB→D Sensing: Depth and Uncertainty from a Video Camera

Neural RGB→D Sensing: Depth and Uncertainty from a Video Camera (CVPR 2019)

Authors: Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa G. Narasimhan, Jan Kautz  
Affiliations: NVIDIA, Carnegie Mellon University, SenseTime

* [http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Neural_RGBrD_Sensing_Depth_and_Uncertainty_From_a_Video_Camera_CVPR_2019_paper.html CVF Mirror] [https://arxiv.org/abs/1901.02571 Arxiv mirror]
* [http://openaccess.thecvf.com/content_CVPR_2019/supplemental/Liu_Neural_RGBrD_Sensing_CVPR_2019_supplemental.zip Supplemental (zip)]

The main ideas here are:
* Estimate a "depth probability distribution" rather than a single value
** For each image, we get a "Depth Probability Volume (DPV)" representing a depth MLE and an uncertainty measure.
* Accumulate DPV estimates across time or across frames.

==Method==
[[File:Figure2 neural rgbrd cvpr2019.png |center|600px|thumb]]
* They first estimate the DPV using a network called the D-Net.
* Next they calculate the difference between the current predicted DPV and the previous DPV. 
*: This residual is passed through the K-Net to create an update. 
*: The update is added to the previous DPV to create the updated DPV.
* An R-Net refines the updated DPV using input image features from the D-Net.

==Architecture==
See their supplementary material for details.

===D-Net===
The D-Net consists of 28 convolutional blocks followed by 4 branches of spatial pyramid layers and a fusion layer.
===K-Net===
===R-Net===




==Evaluation==

==References==
[[Category: Papers]]