Intelligent Systems
Note: This research group has relocated.

7 results (View BibTeX file of all listed publications)

2024

no image
Attention Normalization Impacts Cardinality Generalization in Slot Attention

Krimmel, M., Achterhold, J., Stueckler, J.

In Transactions on Machine Learning Research (TMLR), 2024 (article)

Abstract
Object-centric scene decompositions are important representations for downstream tasks in fields such as computer vision and robotics. The recently proposed Slot Attention module, already leveraged by several derivative works for image segmentation and object tracking in videos, is a deep learning component which performs unsupervised object-centric scene decomposition on input images. It is based on an attention architecture, in which latent slot vectors, which hold compressed information on objects, attend to localized perceptual features from the input image. In this paper, we demonstrate that design decisions on normalizing the aggregated values in the attention architecture have considerable impact on the capabilities of Slot Attention to generalize to a higher number of slots and objects as seen during training. We propose and investigate alternatives to the original normalization scheme which increase the generalization capabilities of Slot Attention to varying slot and object counts, resulting in performance gains on the task of unsupervised image segmentation. The newly proposed normalizations represent minimal and easy to implement modifications of the usual Slot Attention module, changing the value aggregation mechanism from a weighted mean operation to a scaled weighted sum operation.

preprint source code video link (url) [BibTex]

no image
Event-based Non-Rigid Reconstruction of Low-Rank Parametrized Deformations from Contours

Xue, Y., Li, H., Leutenegger, S., Stueckler, J.

International Journal of Computer Vision (IJCV), 2024 (article)

Abstract
Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. In this paper, we propose a novel approach for reconstructing such deformations using event measurements. Under the assumption of a static background, where all events are generated by the motion, our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework. It associates events to mesh faces on the contour and maximizes the alignment of the line of sight through the event pixel with the associated face. In experiments on synthetic and real data of human body motion, we demonstrate the advantages of our method over state-of-the-art optimization and learning-based approaches for reconstructing the motion of human arms and hands. In addition, we propose an efficient event stream simulator to synthesize realistic event data for human motion.

DOI [BibTex]

Xue, Y., Li, H., Leutenegger, S., Stueckler, J. Event-based Non-Rigid Reconstruction of Low-Rank Parametrized Deformations from Contours International Journal of Computer Vision (IJCV), 2024 (article)

DOI [BibTex]

2022

no image
Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors

Elich, C., Oswald, M. R., Pollefeys, M., Stueckler, J.

Computer Vision and Image Understanding (CVIU), 220, July 2022 (article)

Abstract
Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowledge for learning Multi-Object 3D scene decomposition and representations from single images. Our approach learns to decompose images of synthetic scenes with multiple objects on a planar surface into its constituent scene objects and to infer their 3D properties from a single view. A recurrent encoder regresses a latent representation of 3D shape, pose and texture of each object from an input RGB image. By differentiable rendering, we train our model to decompose scenes from RGB-D images in a self-supervised way. The 3D shapes are represented continuously in function-space as signed distance functions which we pre-train from example shapes in a supervised way. These shape priors provide weak supervision signals to better condition the challenging overall learning task. We evaluate the accuracy of our model in inferring 3D scene layout, demonstrate its generative capabilities, assess its generalization to real images, and point out benefits of the learned representation.

Link Preprint link (url) DOI Project Page [BibTex]

2022

Elich, C., Oswald, M. R., Pollefeys, M., Stueckler, J. Weakly Supervised Learning of Multi-Object 3D Scene Decompositions Using Deep Shape Priors Computer Vision and Image Understanding (CVIU), 220, July 2022 (article)

Link Preprint link (url) DOI Project Page [BibTex]

no image
Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models

Li, H., Stueckler, J.

IEEE Robotics and Automation Letters, 7(3):6415-6422, July 2022, Accepted for oral presentation at IEEE ICRA 2023 (article)

Abstract
Visual-inertial odometry (VIO) is an important technology for autonomous robots with power and payload constraints. In this paper, we propose a novel approach for VIO with stereo cameras which integrates and calibrates the velocity-control based kinematic motion model of wheeled mobile robots online. Including such a motion model can help to improve the accuracy of VIO. Compared to several previous approaches proposed to integrate wheel odometer measurements for this purpose, our method does not require wheel encoders and can be applied when the robot motion can be modeled with velocity-control based kinematic motion model. We use radial basis function (RBF) kernels to compensate for the time delay and deviations between control commands and actual robot motion. The motion model is calibrated online by the VIO system and can be used as a forward model for motion control and planning. We evaluate our approach with data obtained in variously sized indoor environments, demonstrate improvements over a pure VIO method, and evaluate the prediction accuracy of the online calibrated model.

preprint link (url) DOI Project Page Project Page [BibTex]

Li, H., Stueckler, J. Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models IEEE Robotics and Automation Letters, 7(3):6415-6422, July 2022, Accepted for oral presentation at IEEE ICRA 2023 (article)

preprint link (url) DOI Project Page Project Page [BibTex]

2021

no image
Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics

Kandukuri, R., Achterhold, J., Moeller, M., Stueckler, J.

International Journal of Computer Vision, 130, pages: 3-16, 2021 (article)

link (url) DOI Project Page [BibTex]

2021

Kandukuri, R., Achterhold, J., Moeller, M., Stueckler, J. Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics International Journal of Computer Vision, 130, pages: 3-16, 2021 (article)

link (url) DOI Project Page [BibTex]

2020

no image
Numerical Quadrature for Probabilistic Policy Search

Vinogradska, J., Bischoff, B., Achterhold, J., Koller, T., Peters, J.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(1):164-175, 2020 (article)

DOI [BibTex]

2020

Vinogradska, J., Bischoff, B., Achterhold, J., Koller, T., Peters, J. Numerical Quadrature for Probabilistic Policy Search IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(1):164-175, 2020 (article)

DOI [BibTex]

no image
Visual-Inertial Mapping with Non-Linear Factor Recovery

Usenko, V., Demmel, N., Schubert, D., Stückler, J., Cremers, D.

IEEE Robotics and Automation Letters (RA-L), 5(2):422-429, 2020, presented at IEEE International Conference on Robotics and Automation (ICRA) 2020, preprint arXiv:1904.06504 (article)

Abstract
Cameras and inertial measurement units are complementary sensors for ego-motion estimation and environment mapping. Their combination makes visual-inertial odometry (VIO) systems more accurate and robust. For globally consistent mapping, however, combining visual and inertial information is not straightforward. To estimate the motion and geometry with a set of images large baselines are required. Because of that, most systems operate on keyframes that have large time intervals between each other. Inertial data on the other hand quickly degrades with the duration of the intervals and after several seconds of integration, it typically contains only little useful information. In this paper, we propose to extract relevant information for visual-inertial mapping from visual-inertial odometry using non-linear factor recovery. We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO. To obtain a globally consistent map we combine these factors with loop-closing constraints using bundle adjustment. The VIO factors make the roll and pitch angles of the global map observable, and improve the robustness and the accuracy of the mapping. In experiments on a public benchmark, we demonstrate superior performance of our method over the state-of-the-art approaches.

Code Preprint link (url) Project Page [BibTex]

Usenko, V., Demmel, N., Schubert, D., Stückler, J., Cremers, D. Visual-Inertial Mapping with Non-Linear Factor Recovery IEEE Robotics and Automation Letters (RA-L), 5(2):422-429, 2020, presented at IEEE International Conference on Robotics and Automation (ICRA) 2020, preprint arXiv:1904.06504 (article)

Code Preprint link (url) Project Page [BibTex]