SAID-NeRF：面向透明物体深度补全的分割辅助 NeRF
SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objects
AI总结：
本文提出 SAID-NeRF，利用视觉基础模型零样本分割引导 NeRF 同时重建语义场，以提升透明物体深度补全和机器人抓取性能。
摘要：
使用现成的 RGB-D 相机获取透明物体的准确深度信息是计算机视觉与机器人领域中一个众所周知的挑战。深度估计/补全方法通常被采用，并在具有高质量深度标签的数据集上进行训练，这些标签来自仿真、额外传感器或专门的数据采集设置以及已知的 3D 模型。然而，在大规模数据集上获取可靠的深度信息并不容易，这限制了训练的可扩展性和泛化能力。神经辐射场（NeRFs）是一种免学习的方法，已在新视角合成和形状恢复方面展现出广泛的成功。然而，为了准确捕获镜面表面，通常需要启发式方法和受控环境（光照、背景等）。在本文中，我们提出使用视觉基础模型（VFMs）以零样本、无标签的方式进行分割，通过同时重建语义场并引入扩展以增强鲁棒性，从而引导这些物体的 NeRF 重建过程。我们提出的方法——分割辅助 NeRF（SAID-NeRF）在透明物体深度补全数据集和机器人抓取任务上表现出显著性能。
英文摘要：
Acquiring accurate depth information of transparent objects using off-the-shelf RGB-D cameras is a well-known challenge in Computer Vision and Robotics. Depth estimation/completion methods are typically employed and trained on datasets with quality depth labels acquired from either simulation, additional sensors or specialized data collection setups and known 3d models. However, acquiring reliable depth information for datasets at scale is not straightforward, limiting training scalability and generalization. Neural Radiance Fields (NeRFs) are learning-free approaches and have demonstrated wide success in novel view synthesis and shape recovery. However, heuristics and controlled environments (lights, backgrounds, etc) are often required to accurately capture specular surfaces. In this paper, we propose using Visual Foundation Models (VFMs) for segmentation in a zero-shot, label-free way to guide the NeRF reconstruction process for these objects via the simultaneous reconstruction of semantic fields and extensions to increase robustness. Our proposed method Segmentation-AIDed NeRF (SAID-NeRF) shows significant performance on depth completion datasets for transparent objects and robotic grasping.
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。
