An image is taken and then rotated by an arbitrary angle and cropped. Let us assume that the original image is rather meaningless and is not aligned in any way. Given the rotated image, is it possible to learn anything about the original orientation? For example, using: 1. lossy compression artefacts (e.g. some averaging now happening in not axis-aligned rectangles), 2. any artefacts created by the camera sensors (probably camera-dependent).