香港科技大学谭平教授团队与地平线（Horizon Robotics）团队最新发布了一项 3D 场景表征与大规模重建新方法 SAIL-Recon，通过锚点图建立构建场景全局隐式表征，突破现有 VGGT 基础模型对于大规模视觉定位与 3D 重建的处理能力瓶颈，实现万帧级的场景表征抽取与 ...

针对大规模 LiDAR 点云场景分割中高效 Transformer 的发展局限，研究人员提出 3DLST 框架。其含动态超标记优化（DSO）、交叉注意力引导上采样（CAU）模块及 W-net 架构，在 MS-LiDAR（平均 F?分数 89.3%）和 DALES（mIoU 80.2%）表现 SOTA，效率提升 5 倍。 在自动驾驶、城市 ...

The proposed Coordinate-Aware Feature Excitation (CAFE) module and Position-Aware Upsampling (Pos-Up) module both adhere to ...

Stop by Siemens booth and see this amazing demo. You can really see how a transformer works. Gene Wolf has been designing and building substations and other high technology facilities for over 32 ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...