Neural Radiance Fields (NeRFs) are gaining significant interest for online active object reconstruction due to their exceptional memory efficiency and requirement for only posed RGB inputs. Previous NeRF-based view planning methods exhibit computational inefficiency since they rely on an iterative paradigm, consisting of (1) retraining the NeRF when new images arrive; and (2) planning a path to the next best view only. To address these limitations, we propose a non-iterative pipeline based on the Prediction of the Required number of Views (PRV). The key idea behind our approach is that the required number of views to reconstruct an object depends on its complexity. Therefore, we design a deep neural network, named PRVNet, to predict the required number of views, allowing us to tailor the data acquisition based on the object complexity and plan a globally shortest path. To train our PRVNet, we generate supervision labels using the ShapeNet dataset. Simulated experiments show that our PRV-based view planning method outperforms baselines, achieving good reconstruction quality while significantly reducing movement cost and planning time. We further justify the generalization ability of our approach in a real-world experiment.

翻译：神经辐射场（NeRF）因具有出色的内存效率且仅需带位姿的RGB输入，在在线主动物体重建领域引发广泛关注。已有的基于NeRF的视角规划方法因依赖迭代范式而存在计算效率低下问题：该范式需在每张新图像到来时（1）重新训练NeRF；（2）仅规划到下一最优视角的路径。针对这些局限，我们提出基于所需视角数预测（PRV）的非迭代流程。本方法的核心思想在于：重建物体所需的视角数取决于其复杂度。为此，我们设计名为PRVNet的深度神经网络以预测所需视角数，从而能够基于物体复杂度定制数据采集策略并规划全局最短路径。为训练PRVNet，我们利用ShapeNet数据集生成监督标签。仿真实验表明，基于PRV的视角规划方法在保持良好重建质量的同时，显著降低了移动代价和规划时间，性能优于基线方法。我们进一步通过真实世界实验验证了本方法的泛化能力。