Daniel Cremers, IAS Alumni Linde Fellow, and Professor for Computer Vision and Artificial Intelligence at TUM found a way to generate precise 3D reconstructions of objects using images from only two camera perspectives. Their method works even with images captured in their natural surroundings. Previously, such reconstructions were possible only with hundreds of perspectives or under laboratory conditions. Camera-based reconstructions are used in autonomous driving or when preserving historical monuments.
Read more: From two images to a 3D object - TUM