ESAM++：面向边缘设备的高效在线3D感知
ESAM++: Efficient Online 3D Perception on the Edge
用轻量级3D稀疏特征金字塔网络（SFPN）替代ESAM中计算昂贵的3D稀疏UNet，在保持分割精度的同时将推理速度提升至3倍、模型尺寸缩小至一半，为在无GPU加速的边缘设备上部署在线3D感知提供了可复用的高效骨干设计。
原文依据 we propose ESAM++, a lightweight and scalable alternative for online 3D scene perception tailored to edge devices without GPU acceleration
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论实时在线3D场景感知对于机器人、AR/VR和自动驾驶系统至关重要，尤其是在计算资源有限且隐私至关重要的边缘计算场景中。近期如EmbodiedSAM（ESAM）等最优方法通过利用Segment Anything Model（SAM）进行实时、细粒度且泛化的3D实例分割，展示了在线3D感知的潜力。然而，ESAM仍依赖计算昂贵的3D稀疏UNet进行点云特征提取，这占据了3D推理时间的大部分，阻碍了其在资源受限设备上的实用性。本文提出ESAM++，一种面向无GPU加速边缘设备的轻量级且可扩展的在线3D场景感知替代方案。我们的方法引入3D稀疏特征金字塔网络（SFPN），从流式3D点云中高效捕获多尺度几何特征，同时显著降低计算开销和模型尺寸。我们在四个具有挑战性的分割基准（ScanNet、ScanNet200、SceneNN和3RScan）上评估了我们的方法，结果表明，与ESAM相比，我们的模型在保持竞争性精度的同时，推理速度提升高达3倍，模型尺寸缩小至一半，从而能够在边缘设备上实际部署。
英文原文摘要 1332 字符
Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D perception by leveraging the Segment Anything Model (SAM) for real-time, fine-grained, and generalized 3D instance segmentation. However, ESAM still relies on a computationally expensive 3D sparse UNet for point cloud feature extraction, which accounts for the majority of the 3D inference time, hindering its practicality on resource-constrained devices. In this paper, we propose ESAM++, a lightweight and scalable alternative for online 3D scene perception tailored to edge devices without GPU acceleration. Our method introduces a 3D Sparse Feature Pyramid Network (SFPN) that efficiently captures multi-scale geometric features from streaming 3D point clouds while significantly reducing computational overhead and model size. We evaluate our approach on four challenging segmentation benchmarks, namely ScanNet, ScanNet200, SceneNN, and 3RScan, demonstrating that our model achieves competitive accuracy with up to 3x faster inference with a 2x smaller model size compared to ESAM, enabling practical deployment on edge devices.