BoulderBrain is an algorithm for generating indoor bouldering routes by reusing existing holds in new combinations, multiplying the routes available to climbers on a given wall by several fold. Begun as a project for National Taiwan University's Advanced Human Computer Interaction course. Demo video here.
The backend calls Segment Anything from Meta AI Research, FAIR; please install it first.
The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
Install Segment Anything:
pip install git+https://github.com/facebookresearch/segment-anything.git
Click the links below to download the checkpoint for the corresponding model type.
defaultorvit_h: ViT-H SAM model.
or
!wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth
Please input the sample image path, wall information(e.g. id, height, width) in app.py file first.
cd backend
python3 app.py
@article{kirillov2023segany,
title={Segment Anything},
author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
journal={arXiv:2304.02643},
year={2023}
}