OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding
IntermediateSheng-Yu Huang, Jaesung Choe et al.Jan 14arXiv
OpenVoxel is a training-free way to understand 3D scenes by grouping tiny 3D blocks (voxels) into objects and giving each object a clear caption.
#OpenVoxel#Sparse Voxel Rasterization#training-free 3D understanding