Paper accepted at ICIP 2021

We are happy to announce that our paper “SEMANTIC SEGMENTATION IN DEPTH DATA : A COMPARATIVE EVALUATION OF IMAGE AND POINT CLOUD BASED METHODS” has been accepted for publication at the ICIP 2021 IEEE International Conference on Image Processing which will take place from September 19th to 22nd, 2021 at Anchorage, Alaska, USA.

Abstract: The problem of semantic segmentation from depth images can be addressed by segmenting directly in the image domain or at 3D point cloud level. In this paper, we attempt for the first time to provide a study and experimental comparison of the two approaches. Through experiments on three datasets, namely SUN RGB-D, NYUdV2 and TICaM, we extensively compare various semantic segmentation algorithms, the input to which includes images and point clouds derived from them. Based on this, we offer analysis of the performance and computational cost of these algorithms that can provide guidelines on when each method should be preferred.

Authors: Jigyasa Katrolia, Lars Krämer, Jason Rambach, Bruno Mirbach, Didier Stricker



Paper Accepted at CVPR 2021 Conference!

We are proud that our paper “RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2^D-Tree Representation” has been accepted for publication at the Computer Vision Pattern Recognition (CVPR) 2021 Conference, which will take place virtually online from June 19th to 25th. CVPR is the premier annual computer vision conference. Our paper was accepted from ~12000 submissions as one of 23.4% (acceptance rate: 23.4%).

Abstract: We propose RPSRNet – a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel 2^D-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module of our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of ~12-15$\,$ms to register a pair of input point clouds as large as ~250K. Extensive evaluations on (i) KITTI LiDAR-odometry and (ii) ModelNet-40 datasets show that our method outperforms prior state-of-the-art methods – e.g., on the KITTI dataset, DCP-v2 by 1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and disturbance. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

“Rigid Point Set Registration using Barnes-Hut (BH) 2^D-tree
Representation — The center-of-masses (CoMs) and point-densities of
non-empty tree-nodes are computed for the respective BH-trees of the
source and target. These two attributes are input to our RPSRNet which
predicts rigid transformation from the global feature-embedding of the

Authors: Sk Aziz Ali, Kerem Kahraman, Gerd ReisDidier Stricker

To view the paper, please click here.

Paper Accepted in IEEE Access Journal!

We are happy to announce that our paper “Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations” has been accepted for publication in the IEEE Access Journal (Impact Factor: 3.745).

Abstract: This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA). In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. The optimal alignment is obtained by explicit modeling of forces acting on the particles as well as their velocities and displacements with second-order ordinary differential equations of n-body motion. Additional alignment cues can be integrated into FGA through particle masses. We propose a smooth-particle mass function for point mass initialization, which improves robustness to noise and structural discontinuities. To avoid the quadratic complexity of all-to-all point interactions, we adapt a Barnes-Hut tree for accelerated force computation and achieve quasilinear complexity. We show that the new method class has characteristics not found in previous alignment methods such as efficient handling of partial overlaps, inhomogeneous sampling densities, and coping with large point clouds with reduced runtime compared to the state of the art. Experiments show that our method performs on par with or outperforms all compared competing deep-learning-based and general-purpose techniques (which do not take training data) in resolving transformations for LiDAR data and gains state-of-the-art accuracy and speed when coping with different data.

Authors: Sk Aziz Ali, Kerem Kahraman, Christian Theobalt, Didier StrickerVladislav Golyanik

Link to the paper:

DFKI-BMW joint research on Augmented Reality for automotive use cases

In the frame of a research cooperation, DFKI’s Augmented Vision Department and BMW are working jointly on Augmented Reality for In-Car applications. Ahmet Firintepe, a BMW research PhD under the supervision of Dr. Alain Pagani and Prof. Didier Stricker has recently published two papers on outside-in head and glass pose estimation:

Ahmet Firintepe, Alain Pagani and Didier Stricker:
“A Comparison of Single and Multi-View IR image-based AR Glasses Pose Estimation Approaches”
Proc. of the IEEE Virtual Reality conference – Posters. IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (IEEEVR-2021)

In this paper, we present a study on single and multi-view image-based AR glasses pose estimation with two novel methods. The first approach is named GlassPose and is a VGG-based network. The second approach GlassPoseRN is based on ResNet18. We train and evaluate the two custom developed glasses pose estimation networks with one, two and three input images on the HMDPose dataset. We achieve errors as low as 0.10 degrees and 0.90 mm on average on all axes for orientation and translation. For both networks, we observe minimal improvements in position estimation with more input views.

Ahmet Firintepe, Carolin Vey, Stylianos Asteriadis, Alain Pagani, Didier Stricker:
From IR Images to Point Clouds to Pose: Point Cloud-Based AR Glasses Pose Estimation
In: Journal of Imaging 7 80 Seiten 1-18 MDPI 4/2021.

In this paper, we propose two novel AR glasses pose estimation algorithms from single infrared images by using 3D point clouds as an intermediate representation. Our first approach “PointsToRotation” is based on a Deep Neural Network alone, whereas our second approach “PointsToPose” is a hybrid model combining Deep Learning and a voting-based mechanism. Our methods utilize a point cloud estimator, which we trained on multi-view infrared images in a semisupervised manner, generating point clouds based on one image only. We generate a point cloud dataset with our point cloud estimator using the HMDPose dataset, consisting of multi-view infrared images of various AR glasses with the corresponding 6-DoF poses. In comparison to another point cloud-based 6-DoF pose estimation named CloudPose, we achieve an error reduction of around 50%. Compared to a state-of-the-art image-based method, we reduce the pose estimation error by around 96%.

Paper accepted at MDPI Electronics

Our paper “Controlling Teleportation-Based Locomotion in Virtual Reality with Hand Gestures: A Comparative Evaluation of Two-Handed and One-Handed Techniques” got accepted at MDPI Electronics for a Special Issue on Recent Advances in Virtual Reality and Augmented Reality.

Paper: (available as Open Access)
Authors: Alexander SchäferGerd ReisDidier Stricker

Abstract: Virtual Reality (VR) technology offers users the possibility to immerse and freely navigate through virtual worlds. An important component for achieving a high degree of immersion in VR is locomotion. Often discussed in the literature, a natural and effective way of controlling locomotion is still a general problem which needs to be solved. Recently, VR headset manufacturers have been integrating more sensors, allowing hand or eye tracking without any additional required equipment. This enables a wide range of application scenarios with natural freehand interaction techniques where no additional hardware is required. This paper focuses on techniques to control teleportation-based locomotion with hand gestures, where users are able to move around in VR using their hands only. With the help of a comprehensive study involving 21 participants, four different techniques are evaluated. The effectiveness and efficiency as well as user preferences of the presented techniques are determined. Two two-handed and two one-handed techniques are evaluated, revealing that it is possible to move comfortable and effectively through virtual worlds with a single hand only.

TiCAM Dataset for in-Cabin Monitoring released

As part of the research activities of DFKI Augmented Vision in the VIZTA project (, we have published the open-source dataset for automotive in-cabin monitoring with a wide-angle time-of-flight depth sensor. The TiCAM dataset represents a variety of in-car person behavior scenarios and is annotated with 2D/3D bounding boxes, segmentation masks and person activity labels. The dataset is available here The publication describing the dataset in detail is available as a preprint here:

Contacts: Jason Rambach, Jigyasa Katrolia

Paper accepted at ICRA 2021

We are delighted to announce that our paper PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN has been accepted for publication at the ICRA 2021 IEEE International Conference on Robotics and Automation which will take place from May 30 to June 5, 2021 at Xi’an, China.

Abstract: Instance segmentation of planar regions in indoor scenes benefits  visual  SLAM  and  other  applications  such  as augmented reality (AR) where scene understanding is required. Existing  methods  built  upon  two-stage  frameworks  show  satisfactory  accuracy  but  are  limited  by  low  frame  rates.  In this  work,  we  propose  a  real-time  deep  neural  architecture that  estimates  piece-wise  planar  regions  from  a  single  RGB image. Our model employs a variant of a fast single-stage CNN architecture to segment plane instances.  Considering  the  particularity of the target detected, we propose Fast Feature Non-maximum  Suppression  (FF-NMS)  to  reduce  the  suppression errors  resulted  from  overlapping  bounding  boxes  of  planes. We  also  utilize  a  Residual  Feature  Augmentation  module  in the  Feature  Pyramid  Network  (FPN)  .  Our  method  achieves significantly  higher  frame-rates  and  comparable  segmentation accuracy  against  two-stage  methods.  We automatically label over 70,000 images as ground truth from the Stanford 2D-3D-Semantics dataset. Moreover, we incorporate our method with a state-of-the-art planar SLAM and validate  its  benefits.

Authors: Yaxu Xie, Jason Raphael Rambach, Fangwen Shu, Didier Stricker



Two articles published at IEEE Access journal

We are happy to announce that two of our papers have been accepted and published in the IEEE Access journal. IEEE Access is an award-winning, multidisciplinary, all-electronic archival journal, continuously presenting the results of original research or development across all of IEEE’s fields of interest. The articles are published with open access to all readers. The research is part of the BIONIC project and was funded by the European Commission under the Horizon 2020 Programme Grant Agreement n. 826304.

“Simultaneous End User Calibration of Multiple Magnetic Inertial Measurement Units With Associated Uncertainty”
Published in: IEEE Access (Volume: 9)
Page(s): 26468 – 26483
Date of Publication: 05 February 2021
Electronic ISSN: 2169-3536
DOI: 10.1109/ACCESS.2021.3057579

“Magnetometer Robust Deep Human Pose Regression With Uncertainty Prediction Using Sparse Body Worn Magnetic Inertial Measurement Units”
Published in: IEEE Access (Volume: 9)
Page(s): 36657 – 36673
Date of Publication: 26 February 2021
Electronic ISSN: 2169-3536
DOI: 10.1109/ACCESS.2021.3062545

Presentation on Machine Learning and Computer Vision by Dr. Jason Rambach

On March 4th, 2021, Dr. Jason Rambach gave a talk on Machine Learning and Computer Vision at the GIZ (Deutsche Gesellschaft für Internationale Zusammenarbeit) workshop on Machine Learning and Computer Vision for Earth Observation organized by the DFKI MLT department. In the talk, the foundations of Computer Vision, Machine Learning and Deep Learning as well as current Research and Implementation challenges were presented.

Presentation by our senior researcher Dr. Jason Rambach
Agenda of the GIZ workshop on Machine Learning and Computer Vision for Earth Observation

VIZTA project: 18-month public project summary released

DFKI participates in the VIZTA project, coordinated by ST Micrelectronics, aiming  at developing innovative technologies in the field of optical sensors and laser sources for short to long-range 3D-imaging and to demonstrate their value in several key applications including automotive, security, smart buildings, mobile robotics for smart cities, and industry4.0. The 18-month public summary of the project was released, including updates from DFKI Augmented Vision on time-of-flight camera dataset recording and deep learning algorithm development for car in-cabin monitoring and smart building person counting and anomaly detection applications.

Please click here to check out the complete summary.