Thomas Germer

We switched back to JIT compilation today because ahead-of-time compilation caused too many issues. Numba's JIT backend is a bit stricter when checking types.

I think this is a different issue because the error happens in `estimate_alpha_cf` instead of `estimate_foreground_ml`. Anyway, could you create a ["minimal, reproducible example"](https://stackoverflow.com/help/minimal-reproducible-example) with complete code and images so...

@shamindraparui Thank you, I can reproduce the issue. PyMatting expects that all images are in the range [0, 1], but your `img` is in the range [0, 255]. Simply dividing...

@shamindraparui Nice, I am looking forward to the results! For animals, there is also https://github.com/JizhiziLi/GFM and it seems to generalize to other prominent image objects to some degree. Maybe it...

TensorFlow creates intermediate copies of all arrays/tensors, which will take some time. This algorithm is mostly bound by memory bandwidth and not computation. This is why it is important to...

I wrote a mail to [email protected] which was listed on the left side bar of https://www.cs.sfu.ca/~colour/data/shi_gehler/ but the mail bounced. Does anyone know one of the authors and could contact...

There also is a small mistake with the color coding of the image width and height in row 0A0. Two bytes should be red and two bytes should be green....

This sounds like an RGBA image (4 channels) is used instead of an RGB image (3 channels). Maybe it works if you replace line 113 https://github.com/CompVis/latent-diffusion/blob/e66308c7f2e64cb581c6d27ab6fbeb846828253b/notebook_helpers.py#L113 with ```python c =...

NVIDIA seems to have broken their docker images, resulting in the following error message: ``` W: GPG error: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64 InRelease: The following signatures couldn't be verified because the public key...

In Figure 17 on page 14 in [Image Generators with Conditionally-Independent Pixel Synthesis](https://arxiv.org/pdf/2011.13775.pdf) the authors show seamless panoramas generated with a model that has been trained on regular images. I'd...