Reproduce “Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian and 1 more
Kaolin presents a shared PyTorch toolkit for 3D deep learning, bringing together tools for data, representations, models, evaluation, rendering, and visualization. It illustrates training and testing a car-versus-airplane classifier in five lines. The authors report a 110× speedup for generating mesh-adjacency information versus MeshCNN’s reference approach, a selected operation-level comparison, not an end-to-end speedup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.