用背景先验提升透明反光物体抓取的神经表面重建效果
NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection
- 结合变换器与全局先验体素，融合多视角特征并编码空间信息
- 在稀疏视角下仍能实现高精度表面重建，抓取成功率显著优于现有方法
- 特别适合处理透明、反光等难建模物体，适用于真实场景机器人抓取
依赖精确深度信息的抓取方法在面对透明和镜面物体时面临巨大挑战。本文提出NeuGrasp，一种利用背景先验进行材料无关抓取检测的神经表面重建方法。NeuGrasp通过融合变换器与全局先验体积，实现多视角特征的空间编码聚合，在狭窄且稀疏的观测条件下仍具鲁棒性。通过残差特征增强聚焦前景，并利用占据先验体积优化空间感知，有效应对透明与镜面物体的重建难题。在模拟与真实场景中广泛实验表明，NeuGrasp在抓取性能上超越现有最优方法，同时保持相当的重建质量。
原文摘要 · Abstract (English)
Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information. In this paper, we introduce NeuGrasp, a neural surface reconstruction method that leverages background priors for material-agnostic grasp detection. NeuGrasp integrates transformers and global prior volumes to aggregate multi-view features with spatial encoding, enabling robust surface reconstruction in narrow and sparse viewing conditions. By focusing on foreground objects through residual feature enhancement and refining spatial perception with an occupancy-prior volume, NeuGrasp excels in handling objects with transparent and specular surfaces. Extensive experiments in both simulated and real-world scenarios show that NeuGrasp outperforms state-of-the-art methods in grasping while maintaining comparable reconstruction quality. More details are available at https://neugrasp.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。