首页|Institute of Photogrammetry and Remote Sensing Researchers Describe New Findings in Robotics (Novel View Synthesis with Neural Radiance Fields for Industrial Ro bot Applications)
Institute of Photogrammetry and Remote Sensing Researchers Describe New Findings in Robotics (Novel View Synthesis with Neural Radiance Fields for Industrial Ro bot Applications)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in robotic s. According to news reporting out of the Institute of Photogrammetry and Remote Sensing by NewsRx editors, research stated, "Neural Radiance Fields (NeRFs) hav e become a rapidly growing research field with the potential to revolutionize ty pical photogrammetric workflows, such as those used for 3D scene reconstruction. As input, NeRFs require multi-view images with corresponding camera poses as we ll as the interior orientation." The news correspondents obtained a quote from the research from Institute of Pho togrammetry and Remote Sensing: "In the typical NeRF workflow, the camera poses and the interior orientation are estimated in advance with Structure from Motion (SfM). But the quality of the resulting novel views, which depends on different parameters such as the number and distribution of available images, the accurac y of the related camera poses and interior orientation, but also the reflection characteristics of the depicted scene, is difficult to predict. In addition, SfM is a time-consuming pre-processing step, and its robustness and quality strongl y depend on the image content. Furthermore, the undefined scaling factor of SfM hinders subsequent steps in which metric information is required. In this paper, we evaluate the potential of NeRFs for industrial robot applications. To start with, we propose an alternative to SfM pre-processing: we capture the input imag es with a calibrated camera that is attached to the end effector of an industria l robot and determine accurate camera poses with metric scale based on the robot kinematics. We then investigate the quality of the novel views by comparing the m to ground truth, and by computing an internal quality measure based on ensembl e methods. For evaluation purposes, we acquire multiple datasets that pose chall enges for reconstruction typical of industrial applications, like reflective obj ects, poor texture, and fine structures. We show that the robot-based pose deter mination reaches similar accuracy as SfM in non-demanding cases, while having cl ear advantages in more challenging scenarios."
Institute of Photogrammetry and Remote S ensingEmerging TechnologiesMachine LearningRobotRobotics
NETL
NSTL
