WANG KAIXUAN

Results 5 issues of WANG KAIXUAN

Nice project! I have some questions on the paper and experiments. Since the code is not available yet, I post the questions here and hope to get some discussions. First...

Hi, I found that there are artifacts in the provided disparity maps. The dataset is not useable unless the artifacts are removed. Here I provided a sample: ![image](https://user-images.githubusercontent.com/21083590/62349337-09dd4880-b532-11e9-8f82-d9032b5e17ff.png) ![image](https://user-images.githubusercontent.com/21083590/62349353-15307400-b532-11e9-8464-a5b9fd1732e0.png)

Why the value of gamma_s3, gamma_s2, beta_s3, beta_s2 are all zeros in your provided model weights? If they are all zeros, meaning that they are not functional, right?

There are some transformations in trajectory.log that are not SE3 matrix. For example, in sequence 092, from line 6296 to line 6300: 1259 1259 1260 0 0 0 0.032024 0...