no code implementations • 19 Mar 2024 • Aljoša Ošep, Tim Meinhardt, Francesco Ferroni, Neehar Peri, Deva Ramanan, Laura Leal-Taixé
We propose $\texttt{SAL}$ ($\texttt{S}$egment $\texttt{A}$nything in $\texttt{L}$idar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual supervision.
no code implementations • 29 Feb 2024 • Jenny Seidenschwarz, Aljoša Ošep, Francesco Ferroni, Simon Lucey, Laura Leal-Taixé
Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data without manual supervision.
1 code implementation • 19 Oct 2023 • Abhinav Agarwalla, Xuhua Huang, Jason Ziglar, Francesco Ferroni, Laura Leal-Taixé, James Hays, Aljoša Ošep, Deva Ramanan
Our network is modular by design and optimized for all aspects of both the panoptic segmentation and tracking task.
1 code implementation • ICCV 2023 • Cristiano Saltori, Aljoša Ošep, Elisa Ricci, Laura Leal-Taixé
To answer this question, we design the first experimental setup for studying domain generalization (DG) for LiDAR semantic segmentation (DG-LSS).
no code implementations • CVPR 2023 • Xindi Wu, KwunFung Lau, Francesco Ferroni, Aljoša Ošep, Deva Ramanan
Moreover, we show that our retrieved maps can be used to update or expand existing maps and even show proof-of-concept results for visual localization and image retrieval from spatial graphs.
1 code implementation • 19 Oct 2022 • Vladimir Fomenko, Ismail Elezi, Deva Ramanan, Laura Leal-Taixé, Aljoša Ošep
We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world.
Ranked #2 on Novel Object Detection on LVIS v1.0 val
1 code implementation • 14 Oct 2022 • Patrick Dendorfer, Vladimir Yugay, Aljoša Ošep, Laura Leal-Taixé
While we have significantly advanced short-term tracking performance, bridging longer occlusion gaps remains elusive: state-of-the-art object trackers only bridge less than 10% of occlusions longer than three seconds.
no code implementations • 29 Sep 2022 • Mariia Gladkova, Nikita Korobov, Nikolaus Demmel, Aljoša Ošep, Laura Leal-Taixé, Daniel Cremers
Direct methods have shown excellent performance in the applications of visual odometry and SLAM.
no code implementations • 3 Aug 2022 • Aleksandr Kim, Guillem Brasó, Aljoša Ošep, Laura Leal-Taixé
This allows our graph neural network to learn to effectively encode temporal and spatial interactions and fully leverage contextual and motion cues to obtain final scene interpretation by posing data association as edge classification.
1 code implementation • CVPR 2022 • Neehar Peri, Jonathon Luiten, Mengtian Li, Aljoša Ošep, Laura Leal-Taixé, Deva Ramanan
Object detection and forecasting are fundamental components of embodied perception.
no code implementations • CVPR 2022 • Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Deva Ramanan, Bastian Leibe, Aljoša Ošep, Laura Leal-Taixé
A benchmark that would allow us to perform an apple-to-apple comparison of existing efforts is a crucial first step towards advancing this important research field.
Ranked #3 on Open-World Video Segmentation on BURST-val (using extra training data)
1 code implementation • ICCV 2021 • Sérgio Agostinho, Aljoša Ošep, Alessio Del Bue, Laura Leal-Taixé
However, given the initial rotation estimate supplied by Kabsch, we show we can improve point correspondence learning during model training by extending the original optimization problem.
3 code implementations • 29 Apr 2021 • Aleksandr Kim, Aljoša Ošep, Laura Leal-Taixé
Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time.
Ranked #1 on Multi-Object Tracking and Segmentation on KITTI MOTS
no code implementations • 22 Apr 2021 • Yang Liu, Idil Esen Zulfikar, Jonathon Luiten, Achal Dave, Deva Ramanan, Bastian Leibe, Aljoša Ošep, Laura Leal-Taixé
We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.
1 code implementation • CVPR 2021 • Mehmet Aygün, Aljoša Ošep, Mark Weber, Maxim Maximov, Cyrill Stachniss, Jens Behley, Laura Leal-Taixé
In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points.
Ranked #7 on 4D Panoptic Segmentation on SemanticKITTI
1 code implementation • 23 Feb 2021 • Mark Weber, Jun Xie, Maxwell Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljoša Ošep, Laura Leal-Taixé, Liang-Chieh Chen
The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation.
no code implementations • 15 Oct 2020 • Patrick Dendorfer, Aljoša Ošep, Anton Milan, Konrad Schindler, Daniel Cremers, Ian Reid, Stefan Roth, Laura Leal-Taixé
We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods.
2 code implementations • 2 Oct 2020 • Patrick Dendorfer, Aljoša Ošep, Laura Leal-Taixé
Inspired by human navigation, we model the task of trajectory prediction as an intuitive two-stage process: (i) goal estimation, which predicts the most likely target positions of the agent, followed by a (ii) routing module which estimates a set of plausible trajectories that route towards the estimated goal.
1 code implementation • 26 Aug 2020 • Sabarinath Mahadevan, Ali Athar, Aljoša Ošep, Sebastian Hennen, Laura Leal-Taixé, Bastian Leibe
On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance.
Ranked #14 on Unsupervised Video Object Segmentation on DAVIS 2016 val
1 code implementation • ECCV 2020 • Ali Athar, Sabarinath Mahadevan, Aljoša Ošep, Laura Leal-Taixé, Bastian Leibe
In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos.
Ranked #5 on Unsupervised Video Object Segmentation on DAVIS 2017 (val) (using extra training data)
1 code implementation • 23 Dec 2017 • Aljoša Ošep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform.
no code implementations • 21 Dec 2017 • Aljoša Ošep, Wolfgang Mehner, Paul Voigtlaender, Bastian Leibe
In this paper, we propose a model-free multi-object tracking approach that uses a category-agnostic image segmentation method to track objects.