Jinwook Huh, Jungseok Hong, Suveer Garg, Hyun Soo Park, Volkan Isler
TL;DR本篇论文提出了一种新的自监督视觉伺服方法,用于基于宽基线图像的相机姿态估计,并以前沿的 3D 引导方法相比在 YCB 数据集上表现出了显着的性能提升。
Abstract
One of the challenging input settings for visual servoing is when the initial
and goal camera views are far apart. Such settings are difficult because the
wide baseline can cause drastic changes in object appeara