Learning to reason from uncalibrated wide angle images

我们见证了在许多现实应用中使用具有宽视场（FOV）镜头的相机的需求日益增长，包括安全、增强现实（AR）、医疗保健和自主系统。增加的视野最大限度地减少了成本，能源和计算，因为需要更少的相机。使用这样的透镜的缺点是，它们需要使用透镜校准方法来获得透镜失真轮廓，然后将其用于校正图像，即，消除失真的影响并创建透视投影图像。已经提出了一系列这样的方法，从经典（确定性）到基于深度学习的方法。不幸的是，校准被认为是一个负担，在大多数关键的系统，由于许多预处理和后处理steps.In此提议中，我们建议摆脱“校准和纠正”的范例，而不是直接原因的广角图像。因此，该项目的目标是开发一套理论和实验工具，用于对未校准广角镜头捕获的图像进行场景理解。

We witness an increasing demand of using cameras with wide field of view (FOV) lenses in many real-life applications, including security, augmented reality (AR), healthcare and autonomous systems. The increased field of view minimizes cost, energy and computation since fewer cameras are needed. The downside of using such lenses is that they require the use of lens calibration methods to obtain a lens distortion profile, which is then used to rectify the image-that is, to cancel the effects of distortion and create a perspective projection image. A wide array of such methods, ranging from classical (deterministic) to deep-learning-based have been proposed. Unfortunately, calibration is considered as a burden in most critical systems due to the many pre- and post-processing steps.In this proposal, we propose to break free from the "calibrate-and-rectify" paradigm, and instead directly reason on the wide-angle images. The goal of this project is therefore to develop a set of theoretical and experimental tools for scene understanding on images captured with uncalibrated, wide-angle lenses.