Search

In many practical applications, 3D point cloud analysis requires rotation invariance. In this paper, we present a learnable descriptor invariant under 3D rotations and reflections, i.e., the O(3) actions, utilizing the recently introduced steerable 3D spherical neurons and vector neurons. Specifically, we propose an embedding of the 3D spherical neurons into 4D vector neurons, which leverages end-to-end training of the model. In our approach, we perform TetraTransform--an equivariant embedding of the 3D input into 4D, constructed from the steerable neurons--and extract deeper O(3)-equivariant features using vector neurons. This integration of the TetraTransform into the VN-DGCNN framework, termed TetraSphere, negligibly increases the number of parameters by less than 0.0002%. TetraSphere sets a new state-of-the-art performance classifying randomly rotated real-world object scans of the challenging subsets of ScanObjectNN. Additionally, TetraSphere outperforms all equivariant methods on randomly rotated synthetic data: classifying objects from ModelNet40 and segmenting parts of the ShapeNet shapes. Thus, our results reveal the practical value of steerable 3D spherical neurons for learning in 3D Euclidean space

In this paper, we utilize hyperspheres and regular n-simplexes and propose an approach to learning deep features equivariant under the transformations of nD reflections and rotations, encompassed by the powerful group of O(n). Namely, we propose O(n)-equivariant neurons with spherical decision surfaces that generalize to any dimension n, which we call Deep Equivariant Hyperspheres. We demonstrate how to combine them in a network that directly operates on the basis of the input points and propose an invariant operator based on the relation between two points and a sphere, which as we show, turns out to be a Gram matrix. Using synthetic and real-world data in nD, we experimentally verify our theoretical contributions and find that our approach is superior to the competing methods for O(n)-equivariant benchmark datasets (classification and regression), demonstrating a favorable speed/performance trade-off. The code is available on GitHub.

The Visual Object Tracking challenge VOT2022 is the tenth annual tracker benchmarking activity organized by the VOT initiative. Results of 93 entries are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2022 challenge was composed of seven sub-challenges focusing on different tracking domains: (i) VOT-STs2022 challenge focused on short-term tracking in RGB by segmentation, (ii) VOT-STb2022 challenge focused on short-term tracking in RGB by bounding boxes, (iii) VOT-RTs2022 challenge focused on “real-time” short-term tracking in RGB by segmentation, (iv) VOT-RTb2022 challenge focused on “real-time” short-term tracking in RGB by bounding boxes, (v) VOT-LT2022 focused on long-term tracking, namely coping with target disappearance and reappearance, (vi) VOT-RGBD2022 challenge focused on short-term tracking in RGB and depth imagery, and (vii) VOT-D2022 challenge focused on short-term tracking in depth-only imagery. New datasets were introduced in VOT-LT2022 and VOT-RGBD2022, VOT-ST2022 dataset was refreshed, and a training dataset was introduced for VOT-LT2022. The source code for most of the trackers, the datasets, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net ). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG., Funding Agencies|ELLIIT; Faculty of Computer Science, University of Ljubljana; Institute of Information and communications Technology Planning; Slovenian research agency research program, (J2-2506, P2-0214); Swedish government; Wallenberg research arena for Media and Language; Ashikaga Institute of Technology, AIT; Horizon 2020 Framework Programme, H2020, (899987); Horizon 2020 Framework Programme, H2020; National Science Council, NSC; Ministry of Science, ICT and Future Planning, MSIP, (2021-0-00537); Ministry of Science, ICT and Future Planning, MSIP; Knut och Alice Wallenbergs Stiftelse; Institute for Information and Communications Technology Promotion, IITP; Fundamental Research Funds for the Central Universities, (226-2022-00051); Fundamental Research Funds for the Central Universities

We propose to leverage optical flow features for higher generalization power in semi-supervised video object segmentation. Optical flow is usually exploited as additional guidance information in many computer vision tasks. However, its relevance in video object segmentation was mainly in unsupervised settings or using the optical flow to warp or refine the previously predicted masks. Different from the latter, we propose to directly leverage the optical flow features in the target representation. We show that this enriched representation improves the encoder-decoder approach to the segmentation task. A model to extract the combined information from the optical flow and the image is proposed, which is then used as input to the target model and the decoder network. Unlike previous methods, e.g. in tracking where concatenation is used to integrate information from image data and optical flow, a simple yet effective attention mechanism is exploited in our work. Experiments on DAVIS 2017 and YouTube-VOS 2019 show that integrating the information extracted from optical flow into the original image branch results in a strong performance gain, especially in unseen classes which demonstrates its higher generalization power.

The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative. Results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years. The VOT2021 challenge was composed of four sub-challenges focusing on different tracking domains: (i) VOT-ST2021 challenge focused on short-term tracking in RGB, (ii) VOT-RT2021 challenge focused on "real-time" short-term tracking in RGB, (iii) VOT-LT2021 focused on long-term tracking, namely coping with target disappearance and reappearance and (iv) VOT-RGBD2021 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2021 dataset was refreshed, while VOT-RGBD2021 introduces a training dataset and sequestered dataset for winner identification. The source code for most of the trackers, the datasets, the evaluation kit and the results along with the source code for most trackers are publicly available at the challenge website(1).

This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360 degrees panoramic image around the USV. We design a convolutional neural network (CNN) architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model data in the Fourier domain using a minimum output sum of squared error correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in field trials conducted over 3 days in the archipelago. Our approach provides excellent results by achieving robust position estimates with global positioning system (GPS)-level accuracy in previously unvisited test areas., Funding Agencies|Wallenberg AI, Autonomous Systems, and Software Program (WASP) - Knut and Alice Wallenberg Foundation; Swedish Foundation for Strategic ResearchSwedish Foundation for Strategic Research [RIT 15-0097]; CENIIT grant [18.14]; VR starting grant [2016-05543]

Video object segmentation (VOS) is a highly challengingproblem, since the target object is only defined by a first-frame refer-ence mask during inference. The problem of how to capture and utilizethis limited information to accurately segment the target remains a fun-damental research question. We address this by introducing an end-to-end trainable VOS architecture that integrates a differentiable few-shotlearner. Our learner is designed to predict a powerful parametric modelof the target by minimizing a segmentation error in the first frame. Wefurther go beyond the standard few-shot learning paradigm by learningwhat our target model should learn in order to maximize segmentationaccuracy. We perform extensive experiments on standard benchmarks.Our approach sets a new state-of-the-art on the large-scale YouTube-VOS 2018 dataset by achieving an overall score of 81.5, corresponding toa 2.6% relative improvement over the previous best result. The code andmodels are available at https://github.com/visionml/pytracking., Funding agencies:vThis work was partly supported by the ETH Zürich Fund (OK), a Huawei Technologies Oy (Finland) project, an Amazon AWS grant, Nvidia, ELLIIT Excellence Center, the Wallenberg AI, Autonomous Systems and Software Program (WASP) and the SSF project Symbicloud.

The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The VOT2020 challenge was composed of five sub-challenges focusing on different tracking domains: (i) VOT-ST2020 challenge focused on short-term tracking in RGB, (ii) VOT-RT2020 challenge focused on “real-time” short-term tracking in RGB, (iii) VOT-LT2020 focused on long-term tracking namely coping with target disappearance and reappearance, (iv) VOT-RGBT2020 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2020 challenge focused on long-term tracking in RGB and depth imagery. Only the VOT-ST2020 datasets were refreshed. A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in the VOT-ST challenges. A new VOT Python toolkit that implements all these novelites was introduced. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net ).

In this work, we address the problem of semi-supervised video object segmentation, where the task is to segment a target object in every image of the video sequence, given a ground truth only in the first frame. To be successful it is crucial to robustly handle unpredictable target appearance changes and distracting objects in the background. In this work we obtain a robust and efficient representation of the target by integrating a fast and light-weight discriminative target model into a deep segmentation network. Trained during inference, the target model learns to discriminate between the local appearances of target and background image regions. Its predictions are enhanced to accurate segmentation masks in a subsequent refinement stage.To further improve the segmentation performance, we add a new module trained to generate global target attention vectors, given the input mask and image feature maps. The attention vectors add semantic information about thetarget from a previous frame to the refinement stage, complementing the predictions provided by the target appearance model. Our method is fast and requires no network fine-tuning. We achieve a combined J and F-score of 70.6 on the DAVIS 2019 test-challenge data

This paper investigates the problem of position estimation of unmanned surface vessels (USVs) operating in coastal areas or in the archipelago. We propose a position estimation method where the horizon line is extracted in a 360 degree panoramic image around the USV. We design a CNN architecture to determine an approximate horizon line in the image and implicitly determine the camera orientation (the pitch and roll angles). The panoramic image is warped to compensate for the camera orientation and to generate an image from an approximately level camera. A second CNN architecture is designed to extract the pixelwise horizon line in the warped image. The extracted horizon line is correlated with digital elevation model (DEM) data in the Fourier domain using a MOSSE correlation filter. Finally, we determine the location of the maximum correlation score over the search area to estimate the position of the USV. Comprehensive experiments are performed in a field trial in the archipelago. Our approach provides promising results by achieving position estimates with GPS-level accuracy., Funding agencies:This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.This work was supported by the Swedish Foundation for Strategic Research (Smart Systems: RIT 15-0097).This research is supported by CENIIT grant (18.14), and VR starting grant (2016-05543).

Recent years have shown great progress in driving assistance systems, approaching autonomous driving step by step. Many approaches rely on lane markers however, which limits the system to larger paved roads and poses problems during winter. In this work we explore an alternative approach to visual road following based on online learning. The system learns the current visual appearance of the road while the vehicle is operated by a human. When driving onto a new type of road, the human driver will drive for a minute while the system learns. After training, the human driver can let go of the controls. The present work proposes a novel approach to online perception-action learning for the specific problem of road following, which makes interchangeably use of supervised learning (by demonstration), instantaneous reinforcement learning, and unsupervised learning (self-reinforcement learning). The proposed method, symbiotic online learning of associations and regression (SOLAR), extends previous work on qHebb-learning in three ways: priors are introduced to enforce mode selection and to drive learning towards particular goals, the qHebb-learning methods is complemented with a reinforcement variant, and a self-assessment method based on predictive coding is proposed. The SOLAR algorithm is compared to qHebb-learning and deep learning for the task of road following, implemented on a model RC-car. The system demonstrates an ability to learn to follow paved and gravel roads outdoors. Further, the system is evaluated in a controlled indoor environment which provides quantifiable results. The experiments show that the SOLAR algorithm results in autonomous capabilities that go beyond those of existing methods with respect to speed, accuracy, and functionality.

Estimating the position of a 3-dimensional world point given its 2-dimensional projections in a set of images is a key component in numerous computer vision systems. There are several methods dealing with this problem, ranging from sub-optimal, linear least square triangulation in two views, to finding the world point that minimized the L2-reprojection error in three views. This leads to the statistically optimal estimate under the assumption of Gaussian noise. In this paper we present a solution to the optimal triangulation in three views. The standard approach for solving the three-view triangulation problem is to find a closed-form solution. In contrast to this, we propose a new method based on an iterative scheme. The method is rigorously tested on both synthetic and real image data with corresponding ground truth, on a midrange desktop PC and a Raspberry Pi, a low-end mobile platform. We are able to improve the precision achieved by the closed-form solvers and reach a speed-up of two orders of magnitude compared to the current state-of-the-art solver. In numbers, this amounts to around 300K triangulations per second on the PC and 30K triangulations per second on Raspberry Pi.