Marc Eder
Marc Eder
I am running the code with the sample data that ships with the repo. Speed issues aside, all of the depth outputs I have seen so far (~25 frames) are...
* Added class for creating and working with tangent images as proposed in ["Tangent Images for Mitigating Spherical Distortion"](https://arxiv.org/abs/1912.09390), CVPR 2020. * Class exposes 3 primary functions: 1. Creating tangent...
I am putting together what hopefully will be a PR with some stuff for spherical image feature detection. However, I'm running into the issue of copying features from multiple images,...
I've downloaded the data and stitched the undistorted color, depth, and normal images using the MATLAB toolbox. What I can't seem to figure out, though, is how to apply the...
I am trying to split subtiltes where there are two speakers that show up in the same frame. In my case this is indicated by newlines and hyphens ('\n-'). I...
I want to format my CUDA code (suffixes ".cu" and ".cuh") using the C++ format. How can I specify the formatter to apply to ".cu" and ".cuh" files? Is there...
Why does the [S2Convolution layer](https://github.com/jonas-koehler/s2cnn/blob/master/s2cnn/soft/s2_conv.py#L39) require square inputs? Is there a way around this to explore the use of your convolutions on equirectangular images?
In the paper, you report a negative result that > WGAN training becomes unstable at times when one uses a momentum based optimizer such as Adam [8] (with B1 >...
Comparing your code to the official TensorFlow implementation I believe the kernel size ought to be 3 for the conv1 in the transformer network code ([starting here](https://github.com/fxia22/pointnet.pytorch/blob/master/pointnet.py#L65)). The official implementation...
I'm a bit confused about the generator and discriminator training. Perhaps it's just the semantics, but the DCGAN "starter" code that many published GANs often use (and is promoted here),...