Weishaupt, AndreasBagnato, LuigiVandergheynst, Pierre2010-05-172010-05-172010-05-172010https://infoscience.epfl.ch/handle/20.500.14299/50109Dense three-dimensional reconstruction of a scene from images is a challenging task. Usually, it is achieved by finding correspondences in successive images and computing the distance by means of epipolar geometry. In this paper, we propose a variational framework to solve the depth from motion problem for planar image sequences. We derive camera ego-motion estimation equations and we show how to combine the depth map and ego-motion estimation in a single algorithm. We successfully test our method on synthetic image sequences for general camera translation. Our method is highly parallelizable and thus well adapted for real-time implementation on the GPU.LTS2Structure from MotionVariationalTV-L1GPGPUtext::conference output::conference proceedings::conference paper