Daniel Cremers

TL;DR: It is proved that the proposed convex relaxation approach provides solutions that lie within a bound of the optimal solution of the convex reconstruction problem.

TL;DR: A novel optimization method based on semidefinite programming relaxations is introduced and applied to the combinatorial problem of minimizing quadratic functionals in binary decision variables subject to linear constraints, and the superiority of this approach to relaxations based on spectral graph theory is shown.

TL;DR: A large dataset containing RGB-D image sequences and the ground-truth camera trajectories is provided and an evaluation criterion for measuring the quality of the estimated camera trajectory of visual SLAM systems is proposed.

TL;DR: An efficient solution to jointly estimate the camera motion and a piecewise-rigid scene flow from an RGB-D sequence by performing a two-fold segmentation of the scene, dividing it into geometric clusters that are, in turn, classified as static or moving elements.

TL;DR: In this paper, a conditional generative adversarial network (GAN) was proposed to generate realistic cloth deformation from real data capture, where global shape deformations were recovered from a subspace model learned from 3D data of clothed people in motion, while high frequency details were added to normal maps created using a conditional GAN.