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.

翻译：几何相机标定常为理解图像透视关系的应用所必需。我们提出一种名为“透视场”的表示方法，用于建模图像中的局部透视属性。透视场以朝上向量和纬度值参数化，包含每个像素的相机视角信息。该表示具有诸多优势：它对相机模型假设极弱，且对裁剪、变形、旋转等常见图像编辑操作具有不变性或等变性；同时更易解释且与人类感知相契合。我们训练神经网络预测透视场，并可将预测结果轻松转换为标定参数。通过与基于相机标定的方法对比，我们展示了该方法在多种场景下的鲁棒性，并给出其在图像合成中的示例应用。