News

We are happy to announce that our paper “SynPo-Net–Accurate and Fast CNN-Based 6DoF Object Pose Estimation Using Synthetic Training” has been accepted for publication at the MDPI Sensors journal, Special Issue Object Tracking and Motion Analysis. Sensors (ISSN 1424-8220; CODEN: SENSC9) is the leading international peer-reviewed open access journal on the science and technology of sensors.

Abstract: Estimation and tracking of 6DoF poses of objects in images is a challenging problem of great importance for robotic interaction and augmented reality. Recent approaches applying deep neural networks for pose estimation have shown encouraging results. However, most of them rely on training with real images of objects with severe limitations concerning ground truth pose acquisition, full coverage of possible poses, and training dataset scaling and generalization capability. This paper presents a novel approach using a Convolutional Neural Network (CNN) trained exclusively on single-channel Synthetic images of objects to regress 6DoF object Poses directly (SynPo-Net). The proposed SynPo-Net is a network architecture specifically designed for pose regression and a proposed domain adaptation scheme transforming real and synthetic images into an intermediate domain that is better fit for establishing correspondences. The extensive evaluation shows that our approach significantly outperforms the state-of-the-art using synthetic training in terms of both accuracy and speed. Our system can be used to estimate the 6DoF pose from a single frame, or be integrated into a tracking system to provide the initial pose.

Authors: Yongzhi Su, Jason Raphael Rambach, Alain Pagani, Didier Stricker

Article: https://av.dfki.de/publications/synpo-net-accurate-and-fast-cnn-based-6dof-object-pose-estimation-using-synthetic-training/

Contact: Yongzhi.Su@dfki.de, Jason.Rambach@dfki.de

After two years of collaborative work, the project ArInfuse is inviting for its final workshop on January 28th.

ARinfuse is an Erasmus+ project that aims to infuse skills in Augmented Reality for geospatial information management in the context of utility underground infrastructures, such as water, sewage, electricity, gas and fiber optics. In this field, there is a real need for an accurate positioning of the underground utilities, to avoid damages to the existing infrastructures. Information communication technologies (ICT), in fusion with global navigation satellite systems (GNSS), GIS and geodatabases and augmented/virtual reality (AR/VR) are able to offer the possibility to convert the geospatial information of the underground utilities into a powerful tool for field workers, engineers and managers.
ARinfuse is mainly addressed to technical professional profiles (future and current) in the utility sector that use, or are planning to use AR technology into practical applications of ordinary management and maintenance of utility networks.

The workshop entitled “Exploiting the potential of Augmented Reality & Geospatial Technologies within the utilities sector” is addressed to engineering students and professionals that are interested in the function, appliance and benefits of AR and geospatial technologies in the utilities sector.

The workshop will also introduce the ARinfuse catalogue of training modules on Augmented Reality and Geoinformatics applied within the utility infrastructure sector.

Registration: https://www.arinfuse.eu/arinfuse-online-workshop-register/
More information: https://www.arinfuse.eu/join-the-final-arinfuse-online-event-training-seminar-thursday-28-01-2021/

Contact persons: Dr. Alain Pagani and Narek Minaskan

We are proud to announce that the Augmented Vision group will present three papers in the upcoming ICPR 2020 conference which will take place from January 10th till 15th, 2021. The International Conference on Pattern Recognition (ICPR) is the premier world conference in Pattern Recognition. It covers both theoretical issues and applications of the discipline. The 25th event in this series is organized as an online virtual conference with more than 1800 participants expected.

The three accepted papers are:

1.  HPERL: 3D Human Pose Estimation from RGB and LiDAR
David Michael Fürst, Shriya T. P. Gupta, René Schuster, Oliver Wasenmüller, Didier Stricker
One sentence summary: HPERL proposes a two-stage 3D human pose detector that fuses RGB and LiDAR information for a precise localization in 3D.
Presentation date: PS T3.3, January 12th, 5 pm CET. 

2. ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching
Rishav, René Schuster, Ramy Battrawy, Oliver Wasenmüller, Didier Stricker
One sentence summary: ResFPN extends Feature Pyramid Networks by adding residual connections from higher resolution features maps to obtain stronger and better localized features for dense matching with deep neural networks.
This paper is accepted as an oral presentation (best 6% of all submissions).
Presentation date: OS T5.1, January 12th, 2 pm CET; PS T5.1, January 12th, 5 pm CET.

3. Ghost Target Detection in 3D Radar Data using Point Cloud based Deep Neural Network
Mahdi Chamseddine, Jason Rambach, Oliver Wasenmüller, Didier Stricker
One sentence summary: An extension to PointNet is developed and trained to detect ghost targets in 3D radar point clouds using labels by an automatic labelling algorithm.
Presentation date: PS T1.16, January 15th, 4:30 pm CET.

The Winter Conference on Applications of Computer Vision (WACV 2021) is IEEE’s and the PAMI-TC’s premier meeting on applications of computer vision. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers. In 2021, the conference is organized as a virtual online event from January 5th till 9th, 2021.

The four accepted papers are:

1. SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation
René Schuster, Oliver Wasenmüller, Christian Unger, Didier Stricker
Q/A Session: Oral 1B, January 6th, 7 pm CET.

2. A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions
René Schuster, Christian Unger, Didier Stricker
Q/A Session: Oral 1C, January 6th, 7 pm CET.

3. SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment
Fangwen Shu, Paul Lesur, Yaxu Xie, Alain Pagani, Didier Stricker

Abstract: This paper demonstrates a system capable of combining a sparse, indirect, monocular visual SLAM, with both offline and real-time Multi-View Stereo (MVS) reconstruction algorithms. This combination overcomes many obstacles encountered by autonomous vehicles or robots employed in agricultural environments, such as overly repetitive patterns, need for very detailed reconstructions, and abrupt movements caused by uneven roads. Furthermore, the use of a monocular SLAM makes our system much easier to integrate with an existing device, as we do not rely on a LiDAR (which is expensive and power consuming), or stereo camera (whose calibration is sensitive to external perturbation e.g. camera being displaced). To the best of our knowledge, this paper presents the first evaluation results for monocular SLAM, and our work further explores unsupervised depth estimation on this specific application scenario by simulating RGB-D SLAM to tackle the scale ambiguity, and shows our approach produces econstructions that are helpful to various agricultural tasks. Moreover, we highlight that our experiments provide meaningful insight to improve monocular SLAM systems under agricultural settings.

4. Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function
Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter, Didier Stricker

Abstract: Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously trained machine learning models. Image normalization is hence a valuable preprocessing component to enhance the models’ robustness. To this end, we introduce a new strategy for the cost function formulation of encoder-decoder networks to average out all the unimportant information in the input images (e.g. environmental features and illumination changes) to focus on the reconstruction of the salient features (e.g. class instances). Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety. Its applicability is assessed on three publicly available datasets. We combine the triplet loss as a regularizer in the latent space representation and a nearest neighbour search to improve the generalization to unseen illuminations and class instances. The importance of the aforementioned post-processing is highlighted on an automotive application. To this end, we release a synthetic dataset of sceneries from three different passenger compartments where each scenery is rendered under ten different illumination and environmental conditions: https://sviro.kl.dfki.de

Jameel Malik successfully defended his PhD thesis entitled “Deep Learning-based 3D Hand Pose and Shape Estimation from a Single Depth Image: Methods, Datasets and Application” in the presence of the PhD committee made up of Prof. Dr. Didier Stricker (Technische Universitat Kaiserslautern), Prof. Dr. Karsten Berns (Technische Universitat Kaiserslautern), Prof. Dr. Antonis Argyros (University of Crete) and Prof. Dr. Sebastian Michel (Technische Universitat Kaiserslautern) on Wednesday, November 11th, 2020.

In his thesis, Jameel Malik addressed the unique challenges of 3D hand pose and shape estimation, and proposed several deep learning based methods that achieve the state-of-the-art accuracy on public benchmarks. His work focuses on developing an effective interlink between the hand pose and shape using deep neural networks. This interlink allows to improve the accuracy of both estimates. His recent paper on 3D convolution based hand pose and shape estimation network was accepted at the premier conference IEEE/CVF CVPR 2020.

Jameel Malik recieved his bachelors and master degrees in electrical engineering from University of Engineering and Technology (UET) and National University of Sciences and Technology (NUST) Pakistan, respectively. Since 2017, he has been working at the Augmented Vision (AV) group DFKI as a researcher. His research interests include computer vision and deep learning. 

A week later, on Thurday, November 19th, 2020, Mr. Markus Miezal also successfully defended his PhD thesis entitled “Models, methods and error source investigation for real-time Kalman filter based inertial human body tracking” in front of the PhD committee consisting of Prof. Dr. Didier Stricker (TU Kaiserslautern and DFKI), Prof. Dr. Björn Eskofier (FAU Erlangen) and Prof. Dr. Karsten Berns (TU Kaiserslautern).

The goal of the thesis is to work towards a robust human body tracking system based on inertial sensors. In particular the identification and impact of different error sources on tracking quality are investigated. Finally, the thesis proposes a real-time, magnetometer-free approach for tracking the lower body with ground contact and translation information. Among the first author publications of the contributions, one can find a journal article in MDPI Sensors and a conference paper on the ICRA 2017.

In 2010, Markus Miezal received his diploma in computer science from the University of Bremen, Germany and started working at the Augmented Vision group at DFKI on visual-inertial sensor fusion and body tracking. In 2015, he followed Dr. Gabriele Bleser into the newly founded interdisciplinary research group wearHEALTH at the TU Kaiserslautern, where the research on body tracking continued, focussing on health related applications such as gait analysis. While finishing his PhD thesis, he co-founded the company sci-track GmbH as spin-off from TU KL and DFKI GmbH, which aims to transfer robust inertial human body tracking algorithms as middleware to industry partners. In the future Markus will continue research at university and support the company.

The Project ENNOS integrates color and depth cameras with the capabilities of deep neural networks on a compact FPGA-based platform to create a flexible and powerful optical system with a wide range of applications in production contexts. While FPGAs offer the flexibility to adapt the system to different tasks, they also constrain the size and complexity of the neural networks. The challenge is to transform the large and complex structure of modern neural networks into a small and compact FPGA architecture. To showcase the capabilities of the ENNOS concept three scenarios have been selected. The first scenario covers the automatic anonymization of people during remote diagnosis, the second one addresses semantic 3D scene segmentation for robotic applications and the third one features an assistance system for model identification and stocktaking in large facilities.

During the milestone review a prototype of the ENNOS camera could be presented. It integrates color and depth camera as well as an FPGA for the execution of neural networks in the device. Furthermore, solutions for the three scenarios could be demonstrated successfully with one prototype already running entirely on the ENNOS platform. This demonstrates that the project is on track to achieve its goals and validates the fundamental approach and concept of the project.

Project Partners:
Robert Bosch GmbH
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI)
KSB SE & Co. KGaA
ioxp GmbH
ifm eletronic GmbH*
PMD Technologies AG*

*Associated Partner

Contact: Stephan Krauß
Click here to visit our project page.

We are happy to announce that our paper “TGA: Two-level Group Attention for Assembly State Detection” has been accepted for publication at the IEEE International Symposium on Mixed and Augmented Reality (ISMAR), which will take place online from November 9th to 13th. The IEEE ISMAR is the leading international academic conference in the fields of Augmented Reality and Mixed Reality. The symposium is organized and supported by the IEEE Computer Society, IEEE VGTC and ACM SIGGRAPH.

Abstract: Assembly state detection, i.e., object state detection, has a critical meaning in computer vision tasks, especially in AR assisted assembly. Unlike other object detection problems, the visual difference between different object states can be subtle. For the better learning of such subtle appearance difference, we proposed a two-level group attention module (TGA), which consists of inter-group attention and intro-group attention. The relationship between feature groups as well as the representation within a feature group is simultaneously enhanced. We embedded the proposed TGA module in a popular object detector and evaluated it on two new datasets related to object state estimation. The result shows that our proposed attention module outperforms the baseline attention module.

Authors: Hangfan Liu, Yongzhi Su, Jason Raphael Rambach, Alain Pagani, Didier Stricker

Please find our paper here.

Please also check out our YouTube Video.

Contact: Yongzhi.Su@dfki.de, Jason.Rambach@dfki.de

PTC has acquired ioxp GmbH, a German industrial start-up for cognitive AR and AI software. ioxp is a spin-off from the Augmented Vision Department of the German Research Center for Artificial Intelligence GmbH (DFKI). For more Information click here or here (both articles in German only).

Congratulations to Dr. Vladislav Golyanik! He received the DAGM MVTec Dissertation Award 2020 for his outstanding dissertation on “Robust Methods for Dense Monocular Non-Rigid 3DReconstruction and Alignment of PointClouds”. For more Information please click here.

We are happy to announce that our paper “Generative View Synthesis: From Single-view Semantics to Novel-view Images” has been accepted for publication at the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020), which will take place online from December 6^th to 12^th. NeurIPS is the top conference in the field of Machine Learning. Our paper was accepted from 9454 submissions as one of 1900 (acceptance rate: 20.1%).

Abstract: Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by converting a semantic map into a photorealistic image. We propose to push the envelope further, and introduce Generative View Synthesis (GVS), which can synthesize multiple photorealistic views of a scene given a single semantic map. We show that the sequential application of existing techniques, e.g., semantics-to-image translation followed by monocular view synthesis, fail at capturing the scene’s structure. In contrast, we solve the semantics-to-image translation in concert with the estimation of the 3D layout of the scene, thus producing geometrically consistent novel views that preserve semantic structures. We first lift the input 2D semantic map onto a 3D layered representation of the scene in feature space, thereby preserving the semantic labels of 3D geometric structures. We then project the layered features onto the target views to generate the final novel-view images. We verify the strengths of our method and compare it with several advanced baselines on three different datasets. Our approach also allows for style manipulation and image editing operations, such as the addition or removal of objects, with simple manipulations of the input style images and semantic maps respectively.

Authors: Tewodros Amberbir Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker

Please find our paper here.

Please also check out our video on YouTube.

Please contact Didier Stricker for more information.