OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation

arXiv:2403.14418v1 Announce Type: new
Abstract: The booming of 3D recognition in the 2020s began with the introduction of point cloud transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models, especially in 3D semantic segmentation. However, sparse CNNs are still valuable networks, due to their efficiency treasure, and ease of application. In this work, we reexamine the design distinctions and test the limits of what a sparse CNN can achieve. We discover that the key credit to the performance difference …

abstract application art arxiv began cloud cnns cs.cv efficiency however introduction networks recognition segmentation semantic state state-of-the-art models transformers type