Multi-View Photometric Stereo (MVPS) is a popular method for fine-detailed 3D acquisition of an object from images. Despite its outstanding results on diverse material objects, a typical MVPS experimental setup requires a well-calibrated light source and a monocular camera installed on an immovable base. This restricts the use of MVPS on a movable platform, limiting us from taking MVPS benefits in 3D acquisition for mobile robotics applications. To this end, we introduce a new mobile robotic system for MVPS. While the proposed system brings advantages, it introduces additional algorithmic challenges. Addressing them, in this paper, we further propose an incremental approach for mobile robotic MVPS. Our approach leverages a supervised learning setup to predict per-view surface normal, object depth, and per-pixel uncertainty in model-predicted results. A refined depth map per view is obtained by solving an MVPS-driven optimization problem proposed in this paper. Later, we fuse the refined depth map while tracking the camera pose w.r.t the reference frame to recover globally consistent object 3D geometry. Experimental results show the advantages of our robotic system and algorithm, featuring the local high-frequency surface detail recovery with globally consistent object shape. Our work is beyond any MVPS system yet presented, providing encouraging results on objects with unknown reflectance properties using fewer frames without a tiring calibration and installation process, enabling computationally efficient robotic automation approach to photogrammetry. The proposed approach is nearly 100 times computationally faster than the state-of-the-art MVPS methods such as Kaya et al., (2023), Kaya et al., (2022) while maintaining the similar results when tested on subjects taken from the benchmark DiLiGenT MV dataset (Li et al., 2020). Furthermore, our system and accompanying algorithm is data-efficient, i.e., it uses significantly fewer frames at test time to perform 3D acquisition11The subjects used to train, test, and compare the results can be downloaded from here.

中文翻译：

---

移动机器人多视角光度立体


多视图光度立体 （MVPS） 是一种从图像中对对象进行精细 3D 采集的常用方法。尽管在各种材料物体上都能获得出色的效果，但典型的 MVPS 实验装置需要经过良好校准的光源和安装在固定底座上的单目相机。这限制了 MVPS 在可移动平台上的使用，限制了我们在移动机器人应用的 3D 采集中利用 MVPS 的优势。为此，我们推出了一种新的 MVPS 移动机器人系统。虽然拟议的系统带来了优势，但它也带来了额外的算法挑战。为了解决这些问题，在本文中，我们进一步提出了一种移动机器人 MVPS 的增量方法。我们的方法利用监督学习设置来预测模型预测结果中每个视图的表面法线、对象深度和每个像素的不确定性。通过解决本文提出的 MVPS 驱动的优化问题，可以获得每个视图的精细深度图。稍后，我们在跟踪相机相对于参考帧的姿势时融合细化的深度图，以恢复全局一致的对象 3D 几何图形。实验结果表明了我们的机器人系统和算法的优势，具有局部高频表面细节恢复和全局一致的物体形状。我们的工作超越了迄今为止展示的任何 MVPS 系统，使用更少的帧在具有未知反射率特性的物体上提供了令人鼓舞的结果，而无需繁琐的校准和安装过程，从而实现了计算高效的机器人自动化摄影测量方法。所提出的方法在计算上比最先进的 MVPS 方法（如 Kaya 等人（2023 年）、Kaya 等人）快近 100 倍。，（2022 年），同时在来自基准 DiLiGenT MV 数据集的受试者上进行测试时保持相似的结果（Li等人，2020 年）。此外，我们的系统和随附的算法具有数据效率，即它在测试时使用的帧数明显减少，用于执行 3D 采集11用于训练、测试和比较结果的受试者可以从此处下载。