论文标题
通过渲染并比较焦距和物体姿势估计
Focal Length and Object Pose Estimation via Render and Compare
论文作者
论文摘要
我们引入了焦距，这是一种神经渲染和能力方法，用于估计摄像头6D姿势和相机焦距，只有单个RGB输入图像描绘了已知对象。这项工作的贡献是双重的。首先，我们得出了一个焦距更新规则，该规则扩展了现有的最新渲染和功能6D姿势估计器以解决联合估计任务。其次，我们研究了几种不同的损失函数，以共同估计物体姿势和焦距。我们发现，直接焦距回归与重新投入损失的结合散布了翻译，旋转和焦距的贡献，从而改善了结果。我们显示了三个挑战性基准数据集的结果，这些数据集描绘了不受控制的设置中已知的3D模型。我们证明我们的焦距和6D姿势估计值比现有的最新方法较低。
We introduce FocalPose, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are twofold. First, we derive a focal length update rule that extends an existing state-of-the-art render-and-compare 6D pose estimator to address the joint estimation task. Second, we investigate several different loss functions for jointly estimating the object pose and focal length. We find that a combination of direct focal length regression with a reprojection loss disentangling the contribution of translation, rotation, and focal length leads to improved results. We show results on three challenging benchmark datasets that depict known 3D models in uncontrolled settings. We demonstrate that our focal length and 6D pose estimates have lower error than the existing state-of-the-art methods.
