no code implementations • ECCV 2020 • Neng Qian, Jiayi Wang, Franziska Mueller, Florian Bernard, Vladislav Golyanik, Christian Theobalt
3D hand reconstruction from images is a widely-studied problem in computer vision and graphics, and has a particularly high relevance for virtual and augmented reality.
1 code implementation • 18 Apr 2024 • Viktoria Ehm, Maolin Gao, Paul Roetzer, Marvin Eisenberger, Daniel Cremers, Florian Bernard
Further, we generate a new inter-class dataset for partial-to-partial shape-matching.
no code implementations • 29 Feb 2024 • Dongliang Cao, Marvin Eisenberger, Nafie El Amrani, Daniel Cremers, Florian Bernard
On the one hand, by incorporating spatial maps, our method obtains more accurate and smooth point-wise correspondences compared to previous functional map methods for shape matching.
no code implementations • 20 Oct 2023 • Johan Thunberg, Florian Bernard
We propose a novel non-negative spherical relaxation for optimization problems over binary matrices with injectivity constraints, which in particular has applications in multi-matching and clustering.
no code implementations • 17 Oct 2023 • Dongliang Cao, Paul Roetzer, Florian Bernard
To this end, we propose a self-adaptive functional map solver to adjust the functional map regularisation for different shape matching scenarios, together with a vertex-wise contrastive loss to obtain more discriminative features.
1 code implementation • 12 Oct 2023 • Paul Roetzer, Ahmed Abbas, Dongliang Cao, Florian Bernard, Paul Swoboda
In this work we propose to combine the advantages of learning-based and combinatorial formalisms for 3D shape matching.
no code implementations • 10 Sep 2023 • Viktoria Ehm, Paul Roetzer, Marvin Eisenberger, Maolin Gao, Florian Bernard, Daniel Cremers
Moreover, while in practice one often has only access to partial observations of a 3D shape (e. g. due to occlusion, or scanning artifacts), there do not exist any methods that directly address geometrically consistent partial shape matching.
no code implementations • ICCV 2023 • Maolin Gao, Paul Roetzer, Marvin Eisenberger, Zorah Lähner, Michael Moeller, Daniel Cremers, Florian Bernard
We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for highly non-rigid shapes.
no code implementations • 24 Jul 2023 • Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
Existing certified training methods produce models that achieve high provable robustness guarantees at certain perturbation levels.
no code implementations • 15 May 2023 • Viktoria Ehm, Daniel Cremers, Florian Bernard
Flows in networks (or graphs) play a significant role in numerous computer vision tasks.
1 code implementation • 27 Apr 2023 • Dongliang Cao, Paul Roetzer, Florian Bernard
In contrast, building upon recent insights about the relation between functional maps and point-wise maps, we propose a novel unsupervised loss to couple the functional maps and point-wise maps, and thereby directly obtain point-wise maps without any post-processing.
1 code implementation • CVPR 2023 • Dongliang Cao, Florian Bernard
The matching of 3D shapes has been extensively studied for shapes represented as surface meshes, as well as for shapes represented as point clouds.
no code implementations • 1 Dec 2022 • Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
Many challenges from natural world can be formulated as a graph matching problem.
Ranked #1 on Graph Matching on CUB
1 code implementation • CVPR 2023 • Paul Roetzer, Zorah Lähner, Florian Bernard
We consider the problem of finding a continuous and non-rigid matching between a 2D contour and a 3D mesh.
no code implementations • 4 Oct 2022 • Jiayi Wang, Diogo Luvizon, Franziska Mueller, Florian Bernard, Adam Kortylewski, Dan Casas, Christian Theobalt
Through this, we demonstrate the quality of our probabilistic reconstruction and show that explicit ambiguity modeling is better-suited for this challenging problem.
1 code implementation • 20 Jul 2022 • Dongliang Cao, Florian Bernard
In this paper, we present a novel approach for deep multi-shape matching that ensures cycle-consistent multi-matchings while not depending on an explicit template shape.
1 code implementation • 1 Jul 2022 • Stefan Haller, Lorenz Feineis, Lisa Hutschenreiter, Florian Bernard, Carsten Rother, Dagmar Kainmüller, Paul Swoboda, Bogdan Savchynskyy
To address these shortcomings, we present a comparative study of graph matching algorithms.
1 code implementation • 20 Jun 2022 • Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard
While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias.
1 code implementation • CVPR 2022 • Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé, Florian Bernard, Daniel Cremers
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.
no code implementations • 29 Apr 2022 • Florian Hofherr, Lukas Koestler, Florian Bernard, Daniel Cremers
Neural networks have recently been used to analyze diverse physical systems and to identify the underlying dynamics.
1 code implementation • CVPR 2022 • Paul Roetzer, Paul Swoboda, Daniel Cremers, Florian Bernard
We present a scalable combinatorial algorithm for globally optimizing over the space of geometrically consistent mappings between 3D shapes.
no code implementations • CVPR 2022 • Dominik Muhle, Lukas Koestler, Nikolaus Demmel, Florian Bernard, Daniel Cremers
However, their approach does not take into account uncertainties, so that the accuracy of the estimated relative pose is highly dependent on accurate feature positions in the target frame.
no code implementations • 30 Mar 2022 • Tarun Yenamandra, Ayush Tewari, Nan Yang, Florian Bernard, Christian Theobalt, Daniel Cremers
To this end, we learn a signed distance function (SDF) along with our DDF model to represent a class of shapes.
no code implementations • 4 Feb 2022 • Paul Swoboda, Bjoern Andres, Andrea Hornakova, Florian Bernard, Jannik Irmai, Paul Roetzer, Bogdan Savchynskyy, David Stein, Ahmed Abbas
In order to facilitate algorithm development for their numerical solution, we collect in one place a large number of datasets in easy to read formats for a diverse set of problem classes.
1 code implementation • 8 Dec 2021 • Viktoria Ehm, Daniel Cremers, Florian Bernard
Traditionally, the concept of a shortest path is considered for graphs with scalar edge weights, which makes it possible to compute the length of a path by adding up the individual edge weights.
no code implementations • 21 Oct 2021 • Maximilian Krahn, Florian Bernard, Vladislav Golyanik
This paper proposes a new algorithm for simultaneous graph matching and clustering.
no code implementations • NeurIPS 2021 • Florian Bernard, Daniel Cremers, Johan Thunberg
We address the non-convex optimisation problem of finding a sparse matrix on the Stiefel manifold (matrices with mutually orthogonal columns of unit length) that maximises (or minimises) a quadratic objective function.
no code implementations • 29 Sep 2021 • Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé, Florian Bernard, Daniel Cremers
Our main contribution is deriving a simple and efficient algorithm that performs this backward pass in closed form.
no code implementations • 22 Jun 2021 • Jiayi Wang, Franziska Mueller, Florian Bernard, Suzanne Sorli, Oleksandr Sotnychenko, Neng Qian, Miguel A. Otaduy, Dan Casas, Christian Theobalt
Moreover, we demonstrate that our approach offers previously unseen two-hand tracking performance from RGB, and quantitatively and qualitatively outperforms existing RGB-based methods that were not explicitly designed for two-hand interactions.
no code implementations • 15 Jun 2021 • Franziska Mueller, Micah Davis, Florian Bernard, Oleksandr Sotnychenko, Mickeal Verschoor, Miguel A. Otaduy, Dan Casas, Christian Theobalt
We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands.
no code implementations • 31 Mar 2021 • Zhenzhang Ye, Tarun Yenamandra, Florian Bernard, Daniel Cremers
While these approaches mainly focus on learning node and edge attributes, they completely ignore the 3D geometry of the underlying 3D objects depicted in the 2D images.
Ranked #12 on Graph Matching on PASCAL VOC
no code implementations • CVPR 2021 • Maolin Gao, Zorah Lähner, Johan Thunberg, Daniel Cremers, Florian Bernard
Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer.
1 code implementation • CVPR 2021 • Tarun Yenamandra, Ayush Tewari, Florian Bernard, Hans-Peter Seidel, Mohamed Elgharib, Daniel Cremers, Christian Theobalt
Our approach has the following favorable properties: (i) It is the first full head morphable model that includes hair.
no code implementations • 20 Sep 2020 • Ayush Tewari, Mohamed Elgharib, Mallikarjun B R., Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt
We present the first approach for embedding real portrait images in the latent space of StyleGAN, which allows for intuitive editing of the head pose, facial expression, and scene illumination in the image.
no code implementations • 6 Jul 2020 • Jiayi Wang, Franziska Mueller, Florian Bernard, Christian Theobalt
We propose to use a model-based generative loss for training hand pose estimators on depth images based on a volumetric hand model.
no code implementations • CVPR 2020 • Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt
StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination.
no code implementations • CVPR 2020 • Florian Bernard, Zeeshan Khan Suri, Christian Theobalt
We present a convex mixed-integer programming formulation for non-rigid shape matching.
no code implementations • 14 Jan 2020 • Lingjie Liu, Weipeng Xu, Marc Habermann, Michael Zollhoefer, Florian Bernard, Hyeongwoo Kim, Wenping Wang, Christian Theobalt
In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space.
no code implementations • 24 Oct 2019 • Tarun Yenamandra, Florian Bernard, Jiayi Wang, Franziska Mueller, Christian Theobalt
We consider the problem of inverse kinematics (IK), where one wants to find the parameters of a given kinematic skeleton that best explain a set of observed 3D joint locations.
no code implementations • ICCV 2019 • Florian Bernard, Johan Thunberg, Paul Swoboda, Christian Theobalt
The matching of multiple objects (e. g. shapes or images) is a fundamental problem in vision and graphics.
1 code implementation • 3 Sep 2019 • Bernhard Egger, William A. P. Smith, Ayush Tewari, Stefanie Wuhrer, Michael Zollhoefer, Thabo Beeler, Florian Bernard, Timo Bolkart, Adam Kortylewski, Sami Romdhani, Christian Theobalt, Volker Blanz, Thomas Vetter
In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed.
no code implementations • CVPR 2019 • Ayush Tewari, Florian Bernard, Pablo Garrido, Gaurav Bharaj, Mohamed Elgharib, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt
In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces.
no code implementations • 26 Nov 2018 • Florian Bernard, Johan Thunberg, Paul Swoboda, Christian Theobalt
The matching of multiple objects (e. g. shapes or images) is a fundamental problem in vision and graphics.
no code implementations • 11 Sep 2018 • Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Hyeongwoo Kim, Florian Bernard, Marc Habermann, Wenping Wang, Christian Theobalt
In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of the human, but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person.
no code implementations • 16 Mar 2018 • Florian Bernard, Johan Thunberg, Jorge Goncalves, Christian Theobalt
In order to deal with the inherent non-convexity of the permutation synchronisation problem, we use an initialisation procedure based on a novel rotation scheme applied to the solution of the spectral relaxation.
no code implementations • CVPR 2018 • Ayush Tewari, Michael Zollhöfer, Pablo Garrido, Florian Bernard, Hyeongwoo Kim, Patrick Pérez, Christian Theobalt
To alleviate this problem, we present the first approach that jointly learns 1) a regressor for face shape, expression, reflectance and illumination on the basis of 2) a concurrently learned parametric face model.
no code implementations • CVPR 2018 • Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence.
no code implementations • CVPR 2018 • Florian Bernard, Christian Theobalt, Michael Moeller
In this work we study convex relaxations of quadratic optimisation problems over permutation matrices.
no code implementations • ICCV 2017 • Ayush Tewari, Michael Zollhöfer, Hyeongwoo Kim, Pablo Garrido, Florian Bernard, Patrick Pérez, Christian Theobalt
In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image.
no code implementations • 25 Jan 2017 • Johan Thunberg, Florian Bernard, Jorge Goncalves
This paper addresses the problem of synchronizing orthogonal matrices over directed graphs.
no code implementations • CVPR 2017 • Florian Bernard, Frank R. Schmidt, Johan Thunberg, Daniel Cremers
We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data.
1 code implementation • 26 Feb 2016 • Florian Bernard, Luis Salamanca, Johan Thunberg, Alexander Tack, Dennis Jentsch, Hans Lamecker, Stefan Zachow, Frank Hertel, Jorge Goncalves, Peter Gemmar
Estimating the parameters of the GMM in a maximum a posteriori manner yields the reconstruction of the surface from the given data points.
no code implementations • CVPR 2016 • Florian Bernard, Peter Gemmar, Frank Hertel, Jorge Goncalves, Johan Thunberg
Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation.
no code implementations • 2 Sep 2015 • Johan Thunberg, Florian Bernard, Jorge Goncalves
Two direct or centralized synchronization methods are presented for different graph topologies; the first one for quasi-strongly connected graphs, and the second one for connected graphs.
no code implementations • CVPR 2015 • Florian Bernard, Johan Thunberg, Peter Gemmar, Frank Hertel, Andreas Husch, Jorge Goncalves
Simulations demonstrate that for noisy transformations, a large proportion of missing data and even for wrong correspondence assignments the method delivers encouraging results.