Smaller3d: Smaller Models for 3D Semantic Segmentation Using Minkowski Engine and Knowledge Distillation Methods. (arXiv:2305.03188v1 [cs.CV])

There are various optimization techniques in the realm of 3D, including point
cloud-based approaches that use mesh, texture, and voxels which optimize how
you store, and how do calculate in 3D. These techniques employ methods such as
feed-forward networks, 3D convolutions, graph neural networks, transformers,
and sparse tensors. However, the field of 3D is one of the most computationally
expensive fields, and these methods have yet to achieve their full potential
due to their large capacity, complexity, and computation limits. …

arxiv cloud cloud-based distillation graph graph neural networks knowledge mesh networks neural networks optimization segmentation semantic