论文标题
NERF-RPN：NERF中对象检测的一般框架
NeRF-RPN: A general framework for object detection in NeRFs
论文作者
论文摘要
本文介绍了直接在NERF上运行的第一个重要对象检测框架NERF-RPN。给定预先训练的NERF模型，NERF-RPN旨在检测场景中的所有边界框。通过利用新型体素表示，该表示包含多尺度3D神经体积特征，我们证明可以直接直接回归NERF中的3D边界框，而不会在任何角度呈现NERF。 NERF-RPN是一个通用框架，可以应用于没有类标签的情况下检测对象。我们通过各种主链体系结构，RPN头部设计和损耗功能实验了NERF-RPN。所有这些都可以以端到端的方式进行训练，以估算高质量的3D边界盒。为了促进NERF对象检测的未来研究，我们构建了一个新的基准数据集，该数据集由仔细的标签和清理组成，由合成和现实世界数据组成。代码和数据集可在https://github.com/lyclyc52/nerf_rpn上找到。
This paper presents the first significant object detection framework, NeRF-RPN, which directly operates on NeRF. Given a pre-trained NeRF model, NeRF-RPN aims to detect all bounding boxes of objects in a scene. By exploiting a novel voxel representation that incorporates multi-scale 3D neural volumetric features, we demonstrate it is possible to regress the 3D bounding boxes of objects in NeRF directly without rendering the NeRF at any viewpoint. NeRF-RPN is a general framework and can be applied to detect objects without class labels. We experimented NeRF-RPN with various backbone architectures, RPN head designs and loss functions. All of them can be trained in an end-to-end manner to estimate high quality 3D bounding boxes. To facilitate future research in object detection for NeRF, we built a new benchmark dataset which consists of both synthetic and real-world data with careful labeling and clean up. Code and dataset are available at https://github.com/lyclyc52/NeRF_RPN.
