论文标题
单图像摄像头校准的透视字段
Perspective Fields for Single Image Camera Calibration
论文作者
论文摘要
对于了解图像视角的应用通常需要几何摄像头校准。我们将透视字段提出作为模拟图像局部透视属性的表示形式。透视字段包含有关相机视图的每个像素信息，将参数化为上向量和纬度值。该表示形式具有许多优势，因为它对相机模型的假设最少，并且对常见的图像编辑操作（如裁剪，翘曲和旋转）是不变的或不变的。它也更容易解释，并且与人类的看法保持一致。我们训练神经网络以预测透视场，并且可以轻松地将预测的透视场转换为校准参数。与基于摄像机校准的方法相比，我们在各种情况下都证明了方法的鲁棒性，并在图像合成中显示了示例应用程序。
Geometric camera calibration is often required for applications that understand the perspective of the image. We propose perspective fields as a representation that models the local perspective properties of an image. Perspective Fields contain per-pixel information about the camera view, parameterized as an up vector and a latitude value. This representation has a number of advantages as it makes minimal assumptions about the camera model and is invariant or equivariant to common image editing operations like cropping, warping, and rotation. It is also more interpretable and aligned with human perception. We train a neural network to predict Perspective Fields and the predicted Perspective Fields can be converted to calibration parameters easily. We demonstrate the robustness of our approach under various scenarios compared with camera calibration-based methods and show example applications in image compositing.
