Search Results for author:
Found 66 papers, 24 papers with code
Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images
Furthermore, we introduce a novel neural rendering framework based on rasterization of the learned hair strands.
Predicting Physical Object Properties from Video
Our approach consists of a physics engine and a correction estimator.
ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Poses
Object pose estimation is a key perceptual capability in robotics.
YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression
6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications.
3D Semantic Scene Perception using Distributed Smart Edge Sensors
The proposed perception system provides a complete scene view containing semantically annotated 3D geometry and estimates 3D poses of multiple persons in real time.
Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice
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.
Video Prediction at Multiple Scales with Hierarchical Recurrent Networks
Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames.
Ranked #1 on
Video Prediction
on KTH
(LPIPS metric)
Synthetic-to-Real Domain Adaptation using Contrastive Unpaired Translation
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.
Human and Automatic Speech Recognition Performance on German Oral History Interviews
We investigate the influence of different adaptation data on robustness and generalization for clean and noisy oral history interviews.
A Study on the Ambiguity in Human Annotation of German Oral History Interviews for Perceived Emotion Recognition and Sentiment Analysis
This paper investigates the ambiguity in human perception of emotions and sentiment in German oral history interviews and the impact on machine learning systems.
Semantic Interaction in Augmented Reality Environments for Microsoft HoloLens
We explore this idea using the Microsoft HoloLens, with which we capture indoor environments and display interaction cues with known object classes.
Fourier-based Video Prediction through Relational Object Motion
The ability to predict future outcomes conditioned on observed video frames is crucial for intelligent decision-making in autonomous systems.
Unsupervised Image Decomposition with Phase-Correlation Networks
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.
T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression
We evaluate the performance of our method on the YCB-Video dataset.
Rendering and Tracking the Directional TSDF: Modeling Surface Orientation for Coherent Maps
Dense real-time tracking and mapping from RGB-D images is an important tool for many robotic applications, such as navigation or grasping.
Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles
In this work, we propose a UAV system for real-time semantic inference and fusion of multiple sensor modalities.
NeuralMVS: Bridging Multi-View Stereo and Novel View Synthesis
Our method uses only a sparse set of images as input and can generalize well to novel scenes.
LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images.
SynPick: A Dataset for Dynamic Bin Picking Scene Understanding
We present SynPick, a synthetic dataset for dynamic scene understanding in bin-picking scenarios.
Real-time Pose Estimation from Images for Multiple Humanoid Robots
Pose estimation commonly refers to computer vision methods that recognize people's body postures in images or videos.
6D Object Pose Estimation using Keypoints and Part Affinity Fields
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.
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
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
FaDIV-Syn: Fast Depth-Independent View Synthesis using Soft Masks and Implicit Blending
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction.
Flexible Table Recognition and Semantic Interpretation System
Moreover, to incorporate the extraction of semantic information, we develop a graph-based table interpretation method.
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling
Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets.
Local Frequency Domain Transformer Networks for Video Prediction
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.
Real-time Multi-Adaptive-Resolution-Surfel 6D LiDAR Odometry using Continuous-time Trajectory Optimization
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.
Robust Skeletonization for Plant Root Structure Reconstruction from MRI
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.
Category-Level 3D Non-Rigid Registration from Single-View RGB Images
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.
NAT: Noise-Aware Training for Robust Neural Sequence Labeling
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.
Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics
Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics.
Multi-Staged Cross-Lingual Acoustic Model Adaption for Robust Speech Recognition in Real-World Applications - A Case Study on German Oral History Interviews
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.
Motion Segmentation using Frequency Domain Transformer Networks
Self-supervised prediction is a powerful mechanism to learn representations that capture the underlying structure of the data.
Visual Descriptor Learning from Monocular Video
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.
Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching
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.
3D U-Net for Segmentation of Plant Root MRI Images in Super-Resolution
Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction.
RoboCup 2019 AdultSize Winner NimbRo: Deep Learning Perception, In-Walk Kick, Push Recovery, and Team Play Capabilities
Individual and team capabilities are challenged every year by rule changes and the increasing performance of the soccer teams at RoboCup Humanoid League.
Robotics
ConvPoseCNN: Dense Convolutional 6D Object Pose Estimation
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.
Bonn Activity Maps: Dataset Description
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.
LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images.
Ranked #21 on
3D Semantic Segmentation
on SemanticKITTI
Refining 6D Object Pose Predictions using Abstract Render-and-Compare
Vision as inverse graphics is a promising concept for detailed scene analysis.
NimbRo Robots Winning RoboCup 2018 Humanoid AdultSize Soccer Competitions
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
Utilizing Temporal Information in Deep Convolutional Network for Efficient Soccer Ball Detection and Tracking
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.
Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews
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.
Directional TSDF: Modeling Surface Orientation for Coherent Meshes
Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping.
Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks
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.
Semi-Supervised Semantic Mapping through Label Propagation with Semantic Texture Meshes
We propose to represent the semantic map as a geometrical mesh and a semantic texture coupled at independent resolution.
Value Iteration Networks on Multiple Levels of Abstraction
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.
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
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 #23 on
3D Semantic Segmentation
on SemanticKITTI
Learning Super-resolution 3D Segmentation of Plant Root MRI Images from Few Examples
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.
Detection and Tracking of Small Objects in Sparse 3D Laser Range Data
Detection and tracking of dynamic objects is a key feature for autonomous behavior in a continuously changing environment.
Complex Valued Gated Auto-encoder for Video Frame Prediction
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.
Towards Learning Abstract Representations for Locomotion Planning in High-dimensional State Spaces
We propose a method to represent the cost function as a CNN.
Robotics
Frequency Domain Transformer Networks for Video Prediction
The task of video prediction is forecasting the next frames given some previous frames.
Autonomous Dual-Arm Manipulation of Familiar Objects
The entire pipeline can be executed on-board and is suitable for on-line grasping scenarios.
Robotics
NimbRo-OP2X: Adult-sized Open-source 3D Printed Humanoid Robot
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
Learning Postural Synergies for Categorical Grasping through Shape Space Registration
Grasping knowledge is gathered in a synergy space of the robotic hand built by following a human grasping taxonomy.
Robotics
Real-Time Visual Tracking and Identification for a Team of Homogeneous Humanoid Robots
The use of a team of humanoid robots to collaborate in completing a task is an increasingly important field of research.
Online Visual Robot Tracking and Identification using Deep LSTM Networks
One of the challenges for achieving collaboration in a team of robots is mutual tracking and identification.
Location Dependency in Video Prediction
The task of video prediction requires analyzing the video frames, temporally and spatially, and constructing a model of how the environment evolves.
Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
Our filter module splits the filter task into multiple less complex and more interpretable subtasks.
Robust 6D Object Pose Estimation in Cluttered Scenes using Semantic Segmentation and Pose Regression Networks
Object pose estimation is a crucial prerequisite for robots to perform autonomous manipulation in clutter.
Hierarchical Recurrent Filtering for Fully Convolutional DenseNets
Generating a robust representation of the environment is a crucial ability of learning agents.
RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
Autonomous robotic manipulation in clutter is challenging.
Transferring Category-based Functional Grasping Skills by Latent Space Non-Rigid Registration
Control poses for generating grasping motions are accumulated in the canonical model from grasping definitions of known objects.
Robotics
Learning a Loopy Model For Semantic Segmentation Exactly
We hope that this insight can lead to a reconsideration of the tractability of loopy models in computer vision.
