-
Hi there,
I created my own data set using the Blender software and the training file looks like this:
Movie_Right/New 00000 r
Movie_Right/New 00001 r
Movie_Right/New 00002 r
Movie_Right/New…
-
First of all, this is an excellent initiative!
I noticed that the image recognition currently only works in two dimensions. It does not take into account the "depth" between the user and the camera…
-
大佬，有木有关于GAN网络与SLAM结合的
-
Hi, thank you for opensource such a great work
I found in dataReader, line 146, see also link below. you use depth * 100 / 256, we know that depth / 256 can get depth in meter, why multiply 100, th…
mzy97 updated
4 years ago
-
> Zhu et. al. CVPR 2019,
> Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion.
I belive you intending add links to the paper while you have added it to the author.
-
I need a monodepth estimation to achieve at least 88% accuracy from 80 - 100m , may it possible for now ?
-
In paper _Digging Into Self-Supervised Monocular Depth Estimation_ , the testing result is said to be run on **KITTI 2015**. I wonder what exactly is test data **KITTI 2015**, is that the **raw data c…
-
can you provide some references to this code? I'm so interested in this code
-
-
Hi，
Thanks for your wonderful job，I am confused on that how to apply the robust loss on monodepth Estimation？is it used to instead photo-metirc loss？could you give me more explanation about that？
…