论文标题
CLA-NERF：类别水平的铰接神经辐射场
CLA-NeRF: Category-Level Articulated Neural Radiance Field
论文作者
论文摘要
我们提出了CLA-NERF-类别级别的铰接神经辐射场，可以执行查看合成，部分分割和明确的姿势估计。使用没有CAD模型和无深度的CLA-NERF在对象类别级别进行了训练，但是一组带有地面真相相机姿势和部分段的RGB图像。在推断期间，仅需在已知类别中观察到的3D对象实例的RGB视图（即几射击）即可推断对象部分分割和神经辐射场。鉴于表达姿势作为输入，CLA-NERF可以执行表达感知的音量渲染，以在任何相机姿势下生成相应的RGB图像。此外，可以通过反向渲染来估算物体的明确姿势。在我们的实验中，我们在合成和现实世界数据上评估了五个类别的框架。在所有情况下，我们的方法均显示现实的变形结果和准确的表达姿势估计。我们认为，几乎没有弹出的对象渲染和表达的姿势估计为机器人感知和与看不见的铰接物对象相互作用的姿势估计。
We propose CLA-NeRF -- a Category-Level Articulated Neural Radiance Field that can perform view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained at the object category level using no CAD models and no depth, but a set of RGB images with ground truth camera poses and part segments. During inference, it only takes a few RGB views (i.e., few-shot) of an unseen 3D object instance within the known category to infer the object part segmentation and the neural radiance field. Given an articulated pose as input, CLA-NeRF can perform articulation-aware volume rendering to generate the corresponding RGB image at any camera pose. Moreover, the articulated pose of an object can be estimated via inverse rendering. In our experiments, we evaluate the framework across five categories on both synthetic and real-world data. In all cases, our method shows realistic deformation results and accurate articulated pose estimation. We believe that both few-shot articulated object rendering and articulated pose estimation open doors for robots to perceive and interact with unseen articulated objects.
