.png){kind=icon}
.png){kind=icon}
Return
Dynamic-focus transformer for point cloud segmentation
.png){kind=icon}
OA
AI
DOI：10.3389/frai.2026.1796099.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Transformer-based methods have significantly advanced 3D point cloud segmentation by effectively capturing long-range dependencies. However; the global or fixed-window self-attention mechanisms they often employ suffer from computational redundancy and overfitting due to processing excessive; potentially irrelevant key-value pairs for each query. To address this; we propose the Dynamic-Focus Transformer; a novel architecture that introduces a data-dependent adaptive attention mechanism. Through learned soft point masks; we selectively sparsify keys and values to focus on semantically critical regions. Our method enables flexible; input-adaptive receptive fields without the heavy memory overhead associated with per-point offset learning in deformable designs. Furthermore; when integrated into a U-Net-style encoder-decoder; our method attains a highly efficient balance between modeling capability and computational cost. Extensive experiments on S3DIS and ScanNetv2 benchmarks demonstrate that our method achieves state-of-the-art performance with notably improved efficiency; validating its effectiveness for large-scale point cloud understanding.
Keywords:
lightweight
transformer
point cloud segmentation
adaptive attention
dynamic-focus
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
F
IF:
4.7
Papers:
2.3K
Citations:
4.4K
View more organizations