Minkyun Seo, Hyungtae Lim, Jaesik Park · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31455 · open-access PDF
Los transformadores de nube de puntos tienen como objetivo capturar geometría local detallada y relaciones en una escena a un coste computacional gestionable. Dos enfoques comunes son la atención de la ventana y la atención global. Diferen en cómo permiten la interacción de toda la escena, lo que se refiere al intercambio de información entre los tokens en una escena. La atención de la ventana reduce el coste computacional al restringir la atención a grupos de tokens llamados ventanas; en diseños serializados, cada ventana contiene un número fijo de tokens consecutivos de una secuencia ordenada espacialmente.
Machine translation (Meta M2M100); the English original follows.
Point cloud transformers aim to capture detailed local geometry and relationships across a scene at a manageable computational cost. Two common approaches are window attention and global attention. They differ in how they enable scene-wide interaction, which refers to information exchange among tokens across a scene. Window attention reduces computational cost by restricting self-attention to groups of tokens called windows; in serialized designs, each window contains a fixed number of consecutive tokens from a spatially ordered sequence. Because each block only directly connects tokens within
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31455, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange