Search Results for author: Bastian Leibe

Found 73 papers, 44 papers with code

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

no code implementations1 Jun 2023 Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult, Francis Engelmann, Bastian Leibe, Konrad Schindler, Theodora Kontogianni

We introduce AGILE3D, an efficient, attention-based model that (1) supports simultaneous segmentation of multiple 3D objects, (2) yields more accurate segmentation masks with fewer user clicks, and (3) offers faster inference.

Interactive Segmentation

DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

no code implementations13 Apr 2023 Amit Kumar Rana, Sabarinath Mahadevan, Alexander Hermans, Bastian Leibe

We introduce a more efficient approach, called DynaMITe, in which we represent user interactions as spatio-temporal queries to a Transformer decoder with a potential to segment multiple object instances in a single iteration.

Instance Segmentation Interactive Segmentation +1

Point2Vec for Self-Supervised Representation Learning on Point Clouds

1 code implementation29 Mar 2023 Karim Abou Zeid, Jonas Schult, Alexander Hermans, Bastian Leibe

Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach.

3D Part Segmentation Few-Shot 3D Point Cloud Classification +3

TarViS: A Unified Approach for Target-based Video Segmentation

1 code implementation CVPR 2023 Ali Athar, Alexander Hermans, Jonathon Luiten, Deva Ramanan, Bastian Leibe

A single TarViS model can be trained jointly on a collection of datasets spanning different tasks, and can hot-swap between tasks during inference without any task-specific retraining.

 Ranked #1 on Video Panoptic Segmentation on KITTI-STEP (using extra training data)

Instance Segmentation Panoptic Segmentation +4

Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats

no code implementations29 Dec 2022 István Sárándi, Alexander Hermans, Bastian Leibe

Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset.

3D Human Pose Estimation Dimensionality Reduction

3D Segmentation of Humans in Point Clouds with Synthetic Data

no code implementations1 Dec 2022 Ayça Takmaz, Jonas Schult, Irem Kaftan, Mertcan Akçay, Bastian Leibe, Robert Sumner, Francis Engelmann, Siyu Tang

Our analysis of different training schemes using a combination of synthetic and realistic data shows that synthetic data for pre-training improves performance in a wide variety of segmentation tasks and models.

Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

1 code implementation6 Oct 2022 Jonas Schult, Francis Engelmann, Alexander Hermans, Or Litany, Siyu Tang, Bastian Leibe

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.

3D Instance Segmentation 3D Semantic Instance Segmentation

4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation

1 code implementation29 Sep 2022 Lars Kreuzberg, Idil Esen Zulfikar, Sabarinath Mahadevan, Francis Engelmann, Bastian Leibe

Our voting-based tracklet generation method followed by geometric feature-based aggregation generates significantly improved panoptic LiDAR segmentation quality when compared to modeling the entire 4D volume using Gaussian probability distributions.

Object Proposal Generation Panoptic Segmentation

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

1 code implementation25 Sep 2022 Ali Athar, Jonathon Luiten, Paul Voigtlaender, Tarasha Khurana, Achal Dave, Bastian Leibe, Deva Ramanan

Multiple existing benchmarks involve tracking and segmenting objects in video e. g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is little interaction between them due to the use of disparate benchmark datasets and metrics (e. g. J&F, mAP, sMOTSA).

Multi-Object Tracking Multi-Object Tracking and Segmentation +4

Global Hierarchical Attention for 3D Point Cloud Analysis

no code implementations7 Aug 2022 Dan Jia, Alexander Hermans, Bastian Leibe

For the 3D object detection task, GHA improves the CenterPoint baseline by +0. 5% mAP on the nuScenes dataset, and the 3DETR baseline by +2. 1% mAP25 and +1. 5% mAP50 on ScanNet.

3D Object Detection Inductive Bias +2

Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics

1 code implementation3 Aug 2022 Diego Paez-Granados, Yujie He, David Gonon, Dan Jia, Bastian Leibe, Kenji Suzuki, Aude Billard

Autonomous navigation in highly populated areas remains a challenging task for robots because of the difficulty in guaranteeing safe interactions with pedestrians in unstructured situations.

Autonomous Navigation

Differentiable Soft-Masked Attention

1 code implementation1 Jun 2022 Ali Athar, Jonathon Luiten, Alexander Hermans, Deva Ramanan, Bastian Leibe

Recently, "Masked Attention" was proposed in which a given object representation only attends to those image pixel features for which the segmentation mask of that object is active.

Semantic Segmentation Video Object Segmentation +2

Opening Up Open World Tracking

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.

Multi-Object Tracking

HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images

1 code implementation CVPR 2022 Ali Athar, Jonathon Luiten, Alexander Hermans, Deva Ramanan, Bastian Leibe

Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video.

Semantic Segmentation Video Object Segmentation +1

Mix3D: Out-of-Context Data Augmentation for 3D Scenes

3 code implementations5 Oct 2021 Alexey Nekrasov, Jonas Schult, Or Litany, Bastian Leibe, Francis Engelmann

Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene.

3D Semantic Segmentation

Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud

1 code implementation3 Jul 2021 Dan Jia, Bastian Leibe

In this preliminary work we attempt to apply submanifold sparse convolution to the task of 3D person detection.

Human Detection

2D vs. 3D LiDAR-based Person Detection on Mobile Robots

no code implementations21 Jun 2021 Dan Jia, Alexander Hermans, Bastian Leibe

Person detection is a crucial task for mobile robots navigating in human-populated environments.

Human Detection

Opening up Open-World Tracking

no code implementations22 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.

Multi-Object Tracking

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera

1 code implementation16 Dec 2020 Dan Jia, Mats Steinweg, Alexander Hermans, Bastian Leibe

Through experiments on the JackRabbot dataset with two detector models, DROW3 and DR-SPAAM, we show that self-supervised detectors, trained or fine-tuned with pseudo-labels, outperform detectors trained only on a different dataset.

Human Detection

Reducing the Annotation Effort for Video Object Segmentation Datasets

no code implementations2 Nov 2020 Paul Voigtlaender, Lishu Luo, Chun Yuan, Yong Jiang, Bastian Leibe

We use a deep convolutional network to automatically create pseudo-labels on a pixel level from much cheaper bounding box annotations and investigate how far such pseudo-labels can carry us for training state-of-the-art VOS approaches.

Semantic Segmentation Video Object Segmentation +1

Making a Case for 3D Convolutions for Object Segmentation in Videos

1 code implementation26 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.

Semantic Segmentation Unsupervised Video Object Segmentation +4

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

1 code implementation12 Jul 2020 István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research.

3D Absolute Human Pose Estimation

SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction

1 code implementation2 May 2020 Francis Engelmann, Jörg Stückler, Bastian Leibe

In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images.

Pose Estimation

DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

2 code implementations29 Apr 2020 Dan Jia, Alexander Hermans, Bastian Leibe

Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data.

Human Detection

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

no code implementations ECCV 2020 Umer Rafi, Andreas Doering, Bastian Leibe, Juergen Gall

Instead of training the network for estimating keypoint correspondences on video data, it is trained on a large scale image datasets for human pose estimation using self-supervision.

Multi-Person Pose Estimation Multi-Person Pose Estimation and Tracking +1

3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation

1 code implementation30 Mar 2020 Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner

We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.

3D Instance Segmentation 3D Object Detection +2

Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation

1 code implementation5 Mar 2020 István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Furthermore, as the image space is decoupled from the heatmap space, the network can learn to reason about joints beyond the image boundary.

2D Human Pose Estimation 3D Human Pose Estimation +1

UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking

1 code implementation15 Jan 2020 Jonathon Luiten, Idil Esen Zulfikar, Bastian Leibe

UnOVOST even performs competitively with many semi-supervised video object segmentation algorithms even though it is not given any input as to which objects should be tracked and segmented.

Semantic Segmentation Semi-Supervised Video Object Segmentation +2

Siam R-CNN: Visual Tracking by Re-Detection

1 code implementation CVPR 2020 Paul Voigtlaender, Jonathon Luiten, Philip H. S. Torr, Bastian Leibe

We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking.

object-detection Object Detection +3

Single-Shot Panoptic Segmentation

no code implementations2 Nov 2019 Mark Weber, Jonathon Luiten, Bastian Leibe

We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate.

Instance Segmentation object-detection +2

AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects

1 code implementation10 Oct 2019 Johannes Groß, Aljosa Osep, Bastian Leibe

In this work, we focus on precise 3D track state estimation and propose a learning-based approach for object-centric relative motion estimation of partially observed objects.

3D Pose Estimation Motion Estimation +2

Track to Reconstruct and Reconstruct to Track

1 code implementation30 Sep 2019 Jonathon Luiten, Tobias Fischer, Bastian Leibe

Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction.

3D Reconstruction Multi-Object Tracking +1

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

1 code implementation28 Jul 2019 Francis Engelmann, Theodora Kontogianni, Bastian Leibe

In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification.

3D Semantic Segmentation

Visual Person Understanding through Multi-Task and Multi-Dataset Learning

no code implementations7 Jun 2019 Kilian Pfeiffer, Alexander Hermans, István Sárándi, Mark Weber, Bastian Leibe

We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation.

General Classification Multi-Task Learning +2

BoLTVOS: Box-Level Tracking for Video Object Segmentation

no code implementations9 Apr 2019 Paul Voigtlaender, Jonathon Luiten, Bastian Leibe

Following this paradigm, we present BoLTVOS (Box-Level Tracking for VOS), which consists of an R-CNN detector conditioned on the first-frame bounding box to detect the object of interest, a temporal consistency rescoring algorithm, and a Box2Seg network that converts bounding boxes to segmentation masks.

One-shot visual object segmentation Semantic Segmentation +2

Large-Scale Object Mining for Object Discovery from Unlabeled Video

no code implementations28 Feb 2019 Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe

This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting.

Object Discovery

FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation

3 code implementations CVPR 2019 Paul Voigtlaender, Yuning Chai, Florian Schroff, Hartwig Adam, Bastian Leibe, Liang-Chieh Chen

Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.

Semantic Segmentation Semi-Supervised Video Object Segmentation +1

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

no code implementations2 Oct 2018 Francis Engelmann, Theodora Kontogianni, Jonas Schult, Bastian Leibe

In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds.

3D Semantic Segmentation

Towards Large-Scale Video Video Object Mining

no code implementations19 Sep 2018 Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe

We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting.

How Robust is 3D Human Pose Estimation to Occlusion?

1 code implementation28 Aug 2018 István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe

Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks.

3D Human Pose Estimation 3D Pose Estimation +1

PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation

5 code implementations24 Jul 2018 Jonathon Luiten, Paul Voigtlaender, Bastian Leibe

We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations.

One-shot visual object segmentation Semantic Segmentation +1

Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline

1 code implementation26 Apr 2018 Stefan Breuers, Lucas Beyer, Umer Rafi, Bastian Leibe

In the past decade many robots were deployed in the wild, and people detection and tracking is an important component of such deployments.

Deep Person Detection in 2D Range Data

1 code implementation6 Apr 2018 Lucas Beyer, Alexander Hermans, Timm Linder, Kai O. Arras, Bastian Leibe

Detecting humans is a key skill for mobile robots and intelligent vehicles in a large variety of applications.

Human Detection

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

1 code implementation5 Feb 2018 Francis Engelmann, Theodora Kontogianni, Alexander Hermans, Bastian Leibe

The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving encouraging segmentation results.

3D Semantic Segmentation

Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video

1 code implementation23 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.

Autonomous Driving Object Discovery +1

Track, then Decide: Category-Agnostic Vision-based Multi-Object Tracking

no code implementations21 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.

Image Segmentation Multi-Object Tracking +1

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

no code implementations28 Jun 2017 Paul Voigtlaender, Bastian Leibe

We tackle the task of semi-supervised video object segmentation, i. e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame.

Semantic Segmentation Semi-Supervised Video Object Segmentation +2

The Atari Grand Challenge Dataset

2 code implementations31 May 2017 Vitaly Kurin, Sebastian Nowozin, Katja Hofmann, Lucas Beyer, Bastian Leibe

Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce.

Imitation Learning Reinforcement Learning (RL)

Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters

2 code implementations12 May 2017 Lucas Beyer, Stefan Breuers, Vitaly Kurin, Bastian Leibe

With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong.

In Defense of the Triplet Loss for Person Re-Identification

31 code implementations22 Mar 2017 Alexander Hermans, Lucas Beyer, Bastian Leibe

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning.

Ranked #3 on Person Re-Identification on CUHK03 (Rank-5 metric)

General Classification Metric Learning +1

Keyframe-Based Visual-Inertial Online SLAM with Relocalization

no code implementations7 Feb 2017 Anton Kasyanov, Francis Engelmann, Jörg Stückler, Bastian Leibe

Our visual-inertial SLAM system is based on a real-time capable visual-inertial odometry method that provides locally consistent trajectory and map estimates.

Pose Tracking Simultaneous Localization and Mapping

Superpixels: An Evaluation of the State-of-the-Art

2 code implementations6 Dec 2016 David Stutz, Alexander Hermans, Bastian Leibe

As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison.


DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data

no code implementations8 Mar 2016 Lucas Beyer, Alexander Hermans, Bastian Leibe

We propose a Convolutional Neural Network (CNN) based detector for this task.

Visual Landmark Recognition from Internet Photo Collections: A Large-Scale Evaluation

no code implementations18 Sep 2014 Tobias Weyand, Bastian Leibe

We evaluate how different choices of methods and parameters for the individual pipeline steps affect overall system performance and examine their effects for different query categories such as buildings, paintings or sculptures.

Landmark Recognition

Tracking People and Their Objects

no code implementations CVPR 2013 Tobias Baumgartner, Dennis Mitzel, Bastian Leibe

Current pedestrian tracking approaches ignore important aspects of human behavior.

Cannot find the paper you are looking for? You can Submit a new open access paper.