1 code implementation • 21 Nov 2023 • David Stotko, Nils Wandel, Reinhard Klein
3D reconstruction of dynamic scenes is a long-standing problem in computer graphics and increasingly difficult the less information is available.
no code implementations • 31 Oct 2023 • Saskia Rabich, Patrick Stotko, Reinhard Klein
Fourier PlenOctrees have shown to be an efficient representation for real-time rendering of dynamic Neural Radiance Fields (NeRF).
1 code implementation • 16 Oct 2023 • Leif Van Holland, Ruben Bliersbach, Jan U. Müller, Patrick Stotko, Reinhard Klein
Implicit representations like Neural Radiance Fields (NeRF) showed impressive results for photorealistic rendering of complex scenes with fine details.
no code implementations • 1 Mar 2023 • Elena Trunz, Jonathan Klein, Jan Müller, Lukas Bode, Ralf Sarlette, Michael Weinmann, Reinhard Klein
We investigate the capabilities of neural inverse procedural modeling to infer high-quality procedural yarn models with fiber-level details from single images of depicted yarn samples.
no code implementations • 25 Nov 2022 • Leif Van Holland, Patrick Stotko, Stefan Krumpen, Reinhard Klein, Michael Weinmann
Despite the impressive progress of telepresence systems for room-scale scenes with static and dynamic scene entities, expanding their capabilities to scenarios with larger dynamic environments beyond a fixed size of a few square-meters remains challenging.
no code implementations • 24 Oct 2022 • Lukas Bode, Michael Weinmann, Reinhard Klein
Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand.
1 code implementation • 3 Jun 2022 • Lokesh Veeramacheneni, Moritz Wolter, Reinhard Klein, Jochen Garcke
We introduce canonical weight normalization for convolutional neural networks.
no code implementations • 2 May 2022 • Patrick Stotko, Michael Weinmann, Reinhard Klein
We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators.
3 code implementations • 15 Sep 2021 • Nils Wandel, Michael Weinmann, Michael Neidlin, Reinhard Klein
Second, convolutional neural networks provide fast inference and generalize but either require large amounts of training data or a physics-constrained loss based on finite differences that can lead to inaccuracies and discretization artifacts.
no code implementations • ICLR 2021 • Nils Wandel, Michael Weinmann, Reinhard Klein
Moreover, the trained neural networks offer a differentiable update step to advance the fluid simulation in time and, thus, can be used as efficient differentiable fluid solvers.
3 code implementations • 22 Dec 2020 • Nils Wandel, Michael Weinmann, Reinhard Klein
Our method indicates strong improvements in terms of accuracy, speed and generalization capabilities over current 3D NN-based fluid models.
3 code implementations • 15 Jun 2020 • Nils Wandel, Michael Weinmann, Reinhard Klein
Our models significantly outperform a recent differentiable fluid solver in terms of computational speed and accuracy.
no code implementations • 13 Dec 2019 • Julian Tanke, Oh-Hun Kwon, Patrick Stotko, Radu Alexandru Rosu, Michael Weinmann, Hassan Errami, Sven Behnke, Maren Bennewitz, Reinhard Klein, Andreas Weber, Angela Yao, Juergen Gall
The key prerequisite for accessing the huge potential of current machine learning techniques is the availability of large databases that capture the complex relations of interest.
no code implementations • 29 Nov 2019 • Jan Müller, Reinhard Klein, Michael Weinmann
In current state-of-the-art Wasserstein-GANs this constraint is enforced via gradient norm regularization.
no code implementations • 9 May 2018 • Patrick Stotko, Stefan Krumpen, Matthias B. Hullin, Michael Weinmann, Reinhard Klein
Real-time 3D scene reconstruction from RGB-D sensor data, as well as the exploration of such data in VR/AR settings, has seen tremendous progress in recent years.
Human-Computer Interaction
no code implementations • ICCV 2017 • Jun Li, Reinhard Klein, Angela Yao
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem.
Ranked #67 on Monocular Depth Estimation on NYU-Depth V2
no code implementations • 22 Oct 2015 • Björn Krüger, Anna Vögele, Tobias Willig, Angela Yao, Reinhard Klein, Andreas Weber
We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence.