Ahmad Al-Mughrabi

I did the following and it works ```bash export XLA_PYTHON_CLIENT_PREALLOCATE=false export XLA_FLAGS="--xla_gpu_strict_conv_algorithm_picker=false --xla_gpu_force_compilation_parallelism=1" ```

In ``config.yml``, you need to define the "generator" attribute first ``` default: generator: rrdn ``` Then, you need to download the pre-trained model in ``./weights/`` directory and map it as...

> Edit: > I added a > `img = img.convert("RGB")` I have the same problem, and I solved it by converting the PIL image to cv2 image. See below (sorry...

> TODO: try https://github.com/facebookresearch/detectron2 for image segmentation, as suggested by @pmoulon This is a fascinating topic! I suggest other self-supervised vision transformer approaches, such as DinoV2. I don't know if...

AFAICT, I still have the same problem with this thread. I use Colmap and Intel Realsense t265 to make the poses up to scale. However, the generated meshes are unitless...

Using Anaconda/Linux: I solved my problem as below: ```bash rm -rf build conda install -c nvidia cuda-toolkit cmake . -B build -DCMAKE_CUDA_COMPILER=$(which nvcc) ```

> Hi, Just a question did masking with a white/black background work for you ? +1

Hi @wnorris, Could we have the camera dimensions? I read section 3.5 and couldn't find the information I wanted. More briefly, I wanted to know the distances of the camera...

Thanks a million for replying to my issue. The data was collected with a mobile phone, Huawei Mate 20 Pro, using a custom application implemented in Android Studio to record...

I replicated the results of the paper based on https://dl-acm-org.sire.ub.edu/doi/epdf/10.1145/3347448.3357172. The only question that I hope to have an answer to is. Can we assume these estimated Volumes as a...