no code implementations • 16 Sep 2013 • Andreas Christian Mueller, Sven Behnke
We hope that this insight can lead to a reconsideration of the tractability of loopy models in computer vision.
no code implementations • 14 Sep 2018 • Diego Rodriguez, Sven Behnke
Control poses for generating grasping motions are accumulated in the canonical model from grasping definitions of known objects.
Robotics
no code implementations • 1 Oct 2018 • Max Schwarz, Anton Milan, Arul Selvam Periyasamy, Sven Behnke
Autonomous robotic manipulation in clutter is challenging.
no code implementations • 5 Oct 2018 • Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke
Generating a robust representation of the environment is a crucial ability of learning agents.
no code implementations • 8 Oct 2018 • Arul Selvam Periyasamy, Max Schwarz, Sven Behnke
Object pose estimation is a crucial prerequisite for robots to perform autonomous manipulation in clutter.
no code implementations • 9 Oct 2018 • Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke
Our filter module splits the filter task into multiple less complex and more interpretable subtasks.
1 code implementation • 11 Oct 2018 • Niloofar Azizi, Hafez Farazi, Sven Behnke
The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how the environment evolves.
no code implementations • 11 Oct 2018 • Hafez Farazi, Sven Behnke
One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification.
no code implementations • 15 Oct 2018 • Hafez Farazi, Sven Behnke
The use of a team of humanoid robots to collaborate in completing a task is an increasingly important field of research.
no code implementations • 18 Oct 2018 • Diego Rodriguez, Antonio Di Guardo, Antonio Frisoli, Sven Behnke
Grasping knowledge is gathered in a synergy space of the robotic hand built by following a human grasping taxonomy.
Robotics
1 code implementation • 19 Oct 2018 • Grzegorz Ficht, Hafez Farazi, André Brandenburger, Diego Rodriguez, Dmytro Pavlichenko, Philipp Allgeuer, Mojtaba Hosseini, Sven Behnke
Humanoid robotics research depends on capable robot platforms, but recently developed advanced platforms are often not available to other research groups, expensive, dangerous to operate, or closed-source.
Robotics
no code implementations • 21 Nov 2018 • Dmytro Pavlichenko, Diego Rodriguez, Max Schwarz, Christian Lenz, Arul Selvam Periyasamy, Sven Behnke
The entire pipeline can be executed on-board and is suitable for on-line grasping scenarios.
Robotics
1 code implementation • 1 Mar 2019 • Hafez Farazi, Sven Behnke
The task of video prediction is forecasting the next frames given some previous frames.
no code implementations • 6 Mar 2019 • Tobias Klamt, Sven Behnke
We propose a method to represent the cost function as a CNN.
Robotics
no code implementations • 8 Mar 2019 • Niloofar Azizi, Nils Wandel, Sven Behnke
Then, we present how a complex neural network can learn such transformations and compare its performance and parameter efficiency to a real-valued gated autoencoder.
no code implementations • 14 Mar 2019 • Jan Razlaw, Jan Quenzel, Sven Behnke
Detection and tracking of dynamic objects is a key feature for autonomous behavior in a continuously changing environment.
no code implementations • 16 Mar 2019 • Ali Oguz Uzman, Jannis Horn, Sven Behnke
While magnetic resonance imaging (MRI) can be used to obtain 3D images of plant roots, extracting the root structural model is challenging due to highly noisy soil environments and low-resolution of MRI images.
5 code implementations • ICCV 2019 • Jens Behley, Martin Garbade, Andres Milioto, Jan Quenzel, Sven Behnke, Cyrill Stachniss, Juergen Gall
Despite the relevance of semantic scene understanding for this application, there is a lack of a large dataset for this task which is based on an automotive LiDAR.
Ranked #32 on 3D Semantic Segmentation on SemanticKITTI
1 code implementation • 27 May 2019 • Daniel Schleich, Tobias Klamt, Sven Behnke
In contrast to a multiresolution coarse-to-fine VIN implementation which does not employ additional descriptive features, our approach is capable of solving challenging environments, which demonstrates that the proposed method learns to encode useful information in the additional features.
no code implementations • 17 Jun 2019 • Radu Alexandru Rosu, Jan Quenzel, Sven Behnke
We propose to represent the semantic map as a geometrical mesh and a semantic texture coupled at independent resolution.
no code implementations • 7 Aug 2019 • Jörg Wagner, Jan Mathias Köhler, Tobias Gindele, Leon Hetzel, Jakob Thaddäus Wiedemer, Sven Behnke
Our approach is based on a novel technique to defend against adversarial evidence (i. e. faulty evidence due to artefacts) by filtering gradients during optimization.
no code implementations • 14 Aug 2019 • Malte Splietker, Sven Behnke
Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping.
no code implementations • 19 Aug 2019 • Michael Gref, Christoph Schmidt, Sven Behnke, Joachim köhler
In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • 5 Sep 2019 • Hafez Farazi, Grzegorz Ficht, Philipp Allgeuer, Dmytro Pavlichenko, Diego Rodriguez, Andre Brandenburger, Mojtaba Hosseini, Sven Behnke
Over the past few years, the Humanoid League rules have changed towards more realistic and challenging game environments, which encourage teams to advance their robot soccer performances.
Robotics
1 code implementation • 5 Sep 2019 • Anna Kukleva, Mohammad Asif Khan, Hafez Farazi, Sven Behnke
We first solve the detection task for an image using fully convolutional encoder-decoder architecture, and later, we use it as an input to our temporal models and jointly learn the detection task in sequences of images.
no code implementations • 8 Oct 2019 • Arul Selvam Periyasamy, Max Schwarz, Sven Behnke
Vision as inverse graphics is a promising concept for detailed scene analysis.
2 code implementations • 12 Dec 2019 • Radu Alexandru Rosu, Peer Schütt, Jan Quenzel, Sven Behnke
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images.
Ranked #30 on 3D Semantic Segmentation on SemanticKITTI
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 • 16 Dec 2019 • Catherine Capellen, Max Schwarz, Sven Behnke
Instead we propose pixel-wise, dense prediction of both translation and orientation components of the object pose, where the dense orientation is represented in Quaternion form.
2 code implementations • 16 Dec 2019 • Diego Rodriguez, Hafez Farazi, Grzegorz Ficht, Dmytro Pavlichenko, Andre Brandenburger, Mojtaba Hosseini, Oleg Kosenko, Michael Schreiber, Marcel Missura, Sven Behnke
Individual and team capabilities are challenged every year by rule changes and the increasing performance of the soccer teams at RoboCup Humanoid League.
Robotics
no code implementations • 21 Feb 2020 • Yi Zhao, Nils Wandel, Magdalena Landl, Andrea Schnepf, Sven Behnke
Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction.
no code implementations • 8 Apr 2020 • Jan Quenzel, Radu Alexandru Rosu, Thomas Läbe, Cyrill Stachniss, Sven Behnke
We integrate both into stereo estimation as well as visual odometry systems and show clear benefits for typical disparity and direct image registration tasks when using our proposed metric.
no code implementations • 15 Apr 2020 • Umashankar Deekshith, Nishit Gajjar, Max Schwarz, Sven Behnke
In this paper, we propose a novel way to estimate dense correspondence on an RGB image where visual descriptors are learned from video examples by training a fully convolutional network.
1 code implementation • 18 Apr 2020 • Hafez Farazi, Sven Behnke
Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data.
no code implementations • LREC 2020 • Michael Gref, Oliver Walter, Christoph Schmidt, Sven Behnke, Joachim K{\"o}hler
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks in domains that greatly deviate from the conditions represented by the training data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 12 May 2020 • Max Schwarz, Sven Behnke
Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics.
1 code implementation • ACL 2020 • Marcin Namysl, Sven Behnke, Joachim köhler
To this end, we formulate the noisy sequence labeling problem, where the input may undergo an unknown noising process and propose two Noise-Aware Training (NAT) objectives that improve robustness of sequence labeling performed on perturbed input: Our data augmentation method trains a neural model using a mixture of clean and noisy samples, whereas our stability training algorithm encourages the model to create a noise-invariant latent representation.
no code implementations • 17 Aug 2020 • Diego Rodriguez, Florian Huber, Sven Behnke
This is done by training a CNN that infers a deformation field for the visible parts of the canonical model and by employing a learned shape (latent) space for inferring the deformations of the occluded parts.
no code implementations • 27 Oct 2020 • Jannis Horn, Yi Zhao, Nils Wandel, Magdalena Landl, Andrea Schnepf, Sven Behnke
Structural reconstruction of plant roots from MRI is challenging, because of low resolution and low signal-to-noise ratio of the 3D measurements which may lead to disconnectivities and wrongly connected roots.
1 code implementation • 5 May 2021 • Jan Quenzel, Sven Behnke
Simultaneous Localization and Mapping (SLAM) is an essential capability for autonomous robots, but due to high data rates of 3D LiDARs real-time SLAM is challenging.
1 code implementation • 10 May 2021 • Hafez Farazi, Jan Nogga, Sven Behnke
Although these models can predict the future frames, they rely entirely on these recurrent structures to simultaneously perform three distinct tasks: extracting transformations, projecting them into the future, and transforming the current frame.
1 code implementation • Findings (ACL) 2021 • Marcin Namysl, Sven Behnke, Joachim köhler
Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets.
1 code implementation • 25 May 2021 • Marcin Namysl, Alexander M. Esser, Sven Behnke, Joachim köhler
Moreover, to incorporate the extraction of semantic information, we develop a graph-based table interpretation method.
no code implementations • 24 Jun 2021 • Andre Rochow, Max Schwarz, Michael Weinmann, Sven Behnke
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction.
1 code implementation • 28 Jun 2021 • Simon Bultmann, Sven Behnke
We present a novel method for estimation of 3D human poses from a multi-camera setup, employing distributed smart edge sensors coupled with a backend through a semantic feedback loop.
Ranked #2 on 3D Multi-Person Pose Estimation on Campus
no code implementations • 5 Jul 2021 • Moritz Zappel, Simon Bultmann, Sven Behnke
The task of 6D object pose estimation from RGB images is an important requirement for autonomous service robots to be able to interact with the real world.
1 code implementation • 6 Jul 2021 • Arash Amini, Hafez Farazi, Sven Behnke
Pose estimation commonly refers to computer vision methods that recognize people's body postures in images or videos.
1 code implementation • 10 Jul 2021 • Arul Selvam Periyasamy, Max Schwarz, Sven Behnke
We present SynPick, a synthetic dataset for dynamic scene understanding in bin-picking scenarios.
no code implementations • 9 Aug 2021 • Radu Alexandru Rosu, Peer Schütt, Jan Quenzel, Sven Behnke
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images.
1 code implementation • 9 Aug 2021 • Radu Alexandru Rosu, Sven Behnke
Our method uses only a sparse set of images as input and can generalize well to novel scenes.
no code implementations • 14 Aug 2021 • Simon Bultmann, Jan Quenzel, Sven Behnke
In this work, we propose a UAV system for real-time semantic inference and fusion of multiple sensor modalities.
1 code implementation • 18 Aug 2021 • Malte Splietker, Sven Behnke
Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation or grasping.
no code implementations • 22 Sep 2021 • Arash Amini, Arul Selvam Periyasamy, Sven Behnke
We evaluate the performance of our method on the YCB-Video dataset.
2 code implementations • 7 Oct 2021 • Angel Villar-Corrales, Sven Behnke
The ability to decompose scenes into their object components is a desired property for autonomous agents, allowing them to reason and act in their surroundings.
no code implementations • 12 Oct 2021 • Malte Mosbach, Sven Behnke
The ability to predict future outcomes conditioned on observed video frames is crucial for intelligent decision-making in autonomous systems.
no code implementations • 18 Nov 2021 • Peer Schüett, Max Schwarz, Sven Behnke
We explore this idea using the Microsoft HoloLens, with which we capture indoor environments and display interaction cues with known object classes.
no code implementations • 18 Jan 2022 • Michael Gref, Nike Matthiesen, Christoph Schmidt, Sven Behnke, Joachim köhler
We investigate the influence of different adaptation data on robustness and generalization for clean and noisy oral history interviews.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • LREC 2022 • Michael Gref, Nike Matthiesen, Sreenivasa Hikkal Venugopala, Shalaka Satheesh, Aswinkumar Vijayananth, Duc Bach Ha, Sven Behnke, Joachim köhler
This paper investigates the ambiguity in human perception of emotions and sentiment in German oral history interviews and the impact on machine learning systems.
no code implementations • 17 Mar 2022 • Benedikt T. Imbusch, Max Schwarz, Sven Behnke
We utilize a state-of-the-art image-to-image translation method to adapt the synthetic images to the real domain, minimizing the domain gap in a learned manner.
1 code implementation • 17 Mar 2022 • Angel Villar-Corrales, Ani Karapetyan, Andreas Boltres, Sven Behnke
In our experiments, we demonstrate that MSPred accurately predicts future video frames as well as high-level representations (e. g. keypoints or semantics) on bin-picking and action recognition datasets, while consistently outperforming popular approaches for future frame prediction.
Ranked #1 on Video Prediction on KTH (LPIPS metric)
1 code implementation • 29 Mar 2022 • Peer Schütt, Radu Alexandru Rosu, Sven Behnke
Semantic segmentation is a core ability required by autonomous agents, as being able to distinguish which parts of the scene belong to which object class is crucial for navigation and interaction with the environment.
2 code implementations • 3 May 2022 • Simon Bultmann, Sven Behnke
The proposed perception system provides a complete scene view containing semantically annotated 3D geometry and estimates 3D poses of multiple persons in real time.
no code implementations • 5 May 2022 • Arash Amini, Arul Selvam Periyasamy, Sven Behnke
6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications.
no code implementations • 23 May 2022 • Arul Selvam Periyasamy, Catherine Capellen, Max Schwarz, Sven Behnke
Object pose estimation is a key perceptual capability in robotics.
no code implementations • 2 Jun 2022 • Martin Link, Max Schwarz, Sven Behnke
Our approach consists of a physics engine and a correction estimator.
no code implementations • 28 Jul 2022 • Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang, Chenglei Wu, Sven Behnke, Giljoo Nam
Furthermore, we introduce a novel neural rendering framework based on rasterization of the learned hair strands.
1 code implementation • 15 Sep 2022 • Bastian Pätzold, Simon Bultmann, Sven Behnke
The person keypoint detections from multiple views are received at a central backend where they are synchronized, filtered, and assigned to person hypotheses.
no code implementations • 18 Oct 2022 • Simon Bultmann, Jan Quenzel, Sven Behnke
Here, we propose a UAV system for real-time semantic inference and fusion of multiple sensor modalities.
no code implementations • 20 Nov 2022 • Malte Mosbach, Sven Behnke
Grasping objects of different shapes and sizes - a foundational, effortless skill for humans - remains a challenging task in robotics.
no code implementations • 21 Nov 2022 • Arul Selvam Periyasamy, Luis Denninger, Sven Behnke
Using the generated pose labels, we train an ImplicitPDF model to estimate the likelihood of an orientation hypothesis given an RGB image.
no code implementations • 21 Nov 2022 • Julian Hau, Simon Bultmann, Sven Behnke
Objects are represented in the map via their 3D mesh model or as an object-centric volumetric sub-map that can model arbitrary object geometry when no detailed 3D model is available.
1 code implementation • CVPR 2023 • Radu Alexandru Rosu, Sven Behnke
We propose improvements to the two areas by replacing the voxel hash encoding with a permutohedral lattice which optimizes faster, especially for higher dimensions.
no code implementations • 5 Dec 2022 • Malte Mosbach, Kara Moraw, Sven Behnke
Dexterous manipulation with anthropomorphic robot hands remains a challenging problem in robotics because of the high-dimensional state and action spaces and complex contacts.
no code implementations • 30 Jan 2023 • Malte Splietker, Sven Behnke
The recently presented Directional Truncated Signed Distance Function (DTSDF) is an augmentation of the regular TSDF that shows potential for more coherent maps and improved tracking performance.
1 code implementation • 23 Feb 2023 • Angel Villar-Corrales, Ismail Wahdan, Sven Behnke
We propose a novel framework for the task of object-centric video prediction, i. e., extracting the compositional structure of a video sequence, as well as modeling objects dynamics and interactions from visual observations in order to predict the future object states, from which we can then generate subsequent video frames.
no code implementations • 7 Mar 2023 • Simon Bultmann, Raphael Memmesheimer, Sven Behnke
We present an approach for estimating a mobile robot's pose w. r. t.
no code implementations • 24 Apr 2023 • Andre Rochow, Max Schwarz, Michael Schreiber, Sven Behnke
In a quick enrollment step, we capture a sequence of source images from the operator without the VR headset which contain all the important operator-specific appearance information.
no code implementations • 21 Jul 2023 • Arul Selvam Periyasamy, Arash Amini, Vladimir Tsaturyan, Sven Behnke
6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications.
no code implementations • 31 Jul 2023 • Malte Mosbach, Sven Behnke
Tool use, a hallmark feature of human intelligence, remains a challenging problem in robotics due the complex contacts and high-dimensional action space.
no code implementations • 15 Aug 2023 • Sven Behnke, Julie A. Adams, David Locke
The $10M ANA Avatar XPRIZE aimed to create avatar systems that can transport human presence to remote locations in real time.
no code implementations • 27 Sep 2023 • Mayara E. Bonani, Max Schwarz, Sven Behnke
We present a method for self-supervised domain adaptation for the scenario where annotated source domain data (e. g. from synthetic generation) is available, but the target domain data is completely unannotated.
no code implementations • 13 Dec 2023 • Arul Selvam Periyasamy, Vladimir Tsaturyan, Sven Behnke
Object pose estimation is a long-standing problem in computer vision.
no code implementations • 15 Dec 2023 • Andre Rochow, Max Schwarz, Sven Behnke
We present a hybrid method that uses both keypoints and direct visual guidance from a mouth camera.
no code implementations • 2 Feb 2024 • Lennard Bodden, Franziska Schwaiger, Duc Bach Ha, Lars Kreuzberg, Sven Behnke
To the best of our knowledge, our work is the first approach that takes advantage of knowledge distillation in the field of spiking object detection.
no code implementations • 29 Feb 2024 • Julian Spravil, Sebastian Houben, Sven Behnke
For image categorization, HyenaPixel and bidirectional Hyena achieve a competitive ImageNet-1k top-1 accuracy of 83. 0% and 83. 5%, respectively, while outperforming other large-kernel networks.
no code implementations • 13 Mar 2024 • Helin Cao, Sven Behnke
The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything.
no code implementations • 15 Mar 2024 • Malte Mosbach, Sven Behnke
After training a teacher policy to master the motor control based on object pose information, TAPG facilitates guided, yet adaptive, learning of a sensorimotor policy, based on object segmentation.