SparseGrasp：基于稀疏多视图 RGB 图像的 3D 语义 Gaussian Splatting 机器人抓取
SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Images
AI总结：
本文提出 SparseGrasp，利用 DUSt3R、3DGS、视觉基础模型语义特征、PCA 压缩和渲染并比较机制，从稀疏 RGB 视图实现快速可更新的开放词汇机器人抓取。
摘要：
语言引导的机器人抓取是一个快速发展的领域，机器人通过人类语言接收指令以抓取特定物体。然而，现有方法通常依赖密集相机视图，并且难以快速更新场景，这限制了它们在多变环境中的有效性。相比之下，我们提出 SparseGrasp，这是一种新颖的开放词汇机器人抓取系统，能够利用稀疏视图 RGB 图像高效运行，并快速处理场景更新。我们的系统建立在机器人学习中现有计算机视觉模块的基础上，并对其进行了显著增强。具体而言，SparseGrasp 利用 DUSt3R 生成稠密点云，作为 3D Gaussian Splatting（3DGS）的初始化，即使在稀疏监督下也能保持高保真度。重要的是，SparseGrasp 融合了来自近期视觉基础模型的语义感知能力。为进一步提高处理效率，我们重新利用主成分分析（PCA）压缩来自 2D 模型的特征。此外，我们提出一种新颖的渲染并比较策略，可确保快速场景更新，从而在多变环境中实现多轮抓取。实验结果表明，SparseGrasp 在速度和适应性方面均显著优于最先进方法，为多变环境中的多轮抓取提供了鲁棒解决方案。
英文摘要：
Language-guided robotic grasping is a rapidly advancing field where robots are instructed using human language to grasp specific objects. However, existing methods often depend on dense camera views and struggle to quickly update scenes, limiting their effectiveness in changeable environments. In contrast, we propose SparseGrasp, a novel open-vocabulary robotic grasping system that operates efficiently with sparse-view RGB images and handles scene updates fastly. Our system builds upon and significantly enhances existing computer vision modules in robotic learning. Specifically, SparseGrasp utilizes DUSt3R to generate a dense point cloud as the initialization for 3D Gaussian Splatting (3DGS), maintaining high fidelity even under sparse supervision. Importantly, SparseGrasp incorporates semantic awareness from recent vision foundation models. To further improve processing efficiency, we repurpose Principal Component Analysis (PCA) to compress features from 2D models. Additionally, we introduce a novel render-and-compare strategy that ensures rapid scene updates, enabling multi-turn grasping in changeable environments. Experimental results show that SparseGrasp significantly outperforms state-of-the-art methods in terms of both speed and adaptability, providing a robust solution for multi-turn grasping in changeable environment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
