Point Transformer V3: Simpler, Faster, Stronger

arXiv:2312.10035v2 Announce Type: replace
Abstract: This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. Drawing inspiration from recent advances in 3D large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy …

abstract accuracy advances arxiv attention cloud context cs.cv efficiency faster innovation inspiration paper power processing representation representation learning scale trade transformer type