Daniel Cremers

TL;DR: A novel multi-view RGB-D based reconstruction method that tackles camera pose, lighting, albedo, and surface normal estimation via the utilization of a gradient signed distance (gradient-SDF) and optimizes the surface's quantities on the actual surface using its volumetric representation.

TL;DR: This chapter explains how the renown functional maps framework can be extended to tackle the partial setting, and presents a further extension to the multipart case in which one tries to establish correspondence between a collection of shapes.

TL;DR: In this paper, the authors consider the problem of finding (possibly non connected) discrete surfaces spanning a finite set of discrete boundary curves in the three-dimensional space and minimizing a discrete energy involving mean curvature.

TL;DR: This work analytically investigates local regularity properties of the Moreau-envelope function under prox-regularity, which allows it to establish the equivalence between stationary points of the splitting model and the original inf-convolution model, and applies the theory to characterize stationarypoints of the penalty objective, which is minimized by the elastic averaging SGD method for distributed training.

TL;DR: This work proposes a novel spatially continuous framework for convex relaxations based on functional lifting and shows less grid bias, which is easy to implement and allows an efficient primal-dual optimization on GPUs.