Newest papers

MixPT: Point Transformer with Interleaved Window and Global Attention

Minkyun Seo, Hyungtae Lim, Jaesik Park · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31455 · cited by 0 works (OpenAlex) · open-access PDF

Korean

포인트 클라우드 트랜스퍼너는 관리 가능한 계산 비용으로 현장 내의 상세한 블록 지오메트리와 관계를 캡처하는 것을 목표로합니다. 두 가지 공통적인 접근 방식은 창의 관심과 글로벌 관심입니다. 그들은 현장 전체 상호 작용을 가능하게하는 방법에 따라 다릅니다. 현장 내의 토큰 간의 정보 교환을 의미합니다. 창의 관심은 창을 통해 창의 회원의 비용을 감소시키는 것으로 계산 비용을 줄입니다. 글로벌 관심은 대조적으로 창으로 불리는 토큰 그룹에 자기 관심을 제한합니다. 일련된 디자인에서 각 창에는 공간적으로 정렬 된 시퀀스에서 일련의 토큰의 고정 숫자가 들어 있습니다. 각 블록은 동일한 창 내에서 토큰을 직접 연결하기 때문에, 창문

Machine translation (Meta M2M100); the English original follows.

Abstract

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 the same window, information exchange across windows relies on changes in window membership across blocks and hierarchical pooling. Global attention, in contrast, directly connects all tokens within a scene, but computing attention over all token pairs can be costly when the number of tokens is large. To balance computational cost and scene-wide interaction, we introduce MixPT, a point transformer that uses a mix of window and global attention blocks in an interleaved schedule, while retaining a single fixed serialization pattern for its window blocks. For scenes with a large number of tokens, MixPT applies global attention to spatially pooled tokens and returns residual updates to the original-resolution stream. Across indoor and outdoor benchmarks, MixPT achieves competitive accuracy with lower latency than representative window and global attention baselines. We further demonstrate the feasibility of scaling the attention stage in depth by repeating the interleaved pattern of window and global attention blocks.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Window (computing), Serialization, Security token, Transformer, Point cloud

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange