Search Results for author: Laura Leal-Taixé

Found 45 papers, 25 papers with code

Simple Cues Lead to a Strong Multi-Object Tracker

no code implementations9 Jun 2022 Jenny Seidenschwarz, Guillem Brasó, Ismail Elezi, Laura Leal-Taixé

We claim that 1) strong cues can be obtained from little amounts of training data if some key design choices are applied, 2) given these strong cues, standard Hungarian matching-based association is enough to obtain impressive results.

Multi-Object Tracking

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

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation

1 code implementation ICCV 2021 Guillem Brasó, Nikita Kister, Laura Leal-Taixé

We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image.

Multi-Person Pose Estimation

Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images

no code implementations5 Oct 2021 Lukas Kondmann, Aysim Toker, Sudipan Saha, Bernhard Schölkopf, Laura Leal-Taixé, Xiao Xiang Zhu

It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection.

Change Detection

Scalable Sinkhorn Backpropagation

no code implementations29 Sep 2021 Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé, Florian Bernard, Daniel Cremers

Our main contribution is deriving a simple and efficient algorithm that performs this backward pass in closed form.

(Just) A Spoonful of Refinements Helps the Registration Error Go Down

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.

Point Cloud Registration

EagerMOT: 3D Multi-Object Tracking via Sensor Fusion

1 code implementation29 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.

3D Multi-Object Tracking Motion Planning +2

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

Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization

1 code implementation CVPR 2021 Aysim Toker, Qunjie Zhou, Maxim Maximov, Laura Leal-Taixé

The goal of cross-view image based geo-localization is to determine the location of a given street view image by matching it against a collection of geo-tagged satellite images.

Image Generation

4D Panoptic LiDAR Segmentation

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.

Multi-Object Tracking Scene Understanding +1

Learning Intra-Batch Connections for Deep Metric Learning

1 code implementation15 Feb 2021 Jenny Seidenschwarz, Ismail Elezi, Laura Leal-Taixé

To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account.

Image Retrieval Metric Learning

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport

1 code implementation NeurIPS 2020 Marvin Eisenberger, Aysim Toker, Laura Leal-Taixé, Daniel Cremers

We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network.

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

no code implementations15 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.

Computer Vision Multiple Object Tracking +3

Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation

1 code implementation2 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.

Trajectory Prediction

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.

 Ranked #1 on Video Object Segmentation on DAVIS 2016 (using extra training data)

Semantic Segmentation Unsupervised Video Object Segmentation +4

Focus on defocus: bridging the synthetic to real domain gap for depth estimation

1 code implementation CVPR 2020 Maxim Maximov, Kevin Galim, Laura Leal-Taixé

We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images.

 Ranked #1 on Depth Estimation on NYU-Depth V2 (RMSE metric)

Depth Estimation

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

1 code implementation CVPR 2020 Maxim Maximov, Ismail Elezi, Laura Leal-Taixé

In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity.

Action Recognition Computer Vision +2

Planning from Images with Deep Latent Gaussian Process Dynamics

1 code implementation L4DC 2020 Nathanael Bosch, Jan Achterhold, Laura Leal-Taixé, Jörg Stückler

We propose to learn a deep latent Gaussian process dynamics (DLGPD) model that learns low-dimensional system dynamics from environment interactions with visual observations.

Gaussian Processes Transfer Learning

MOT20: A benchmark for multi object tracking in crowded scenes

1 code implementation19 Mar 2020 Patrick Dendorfer, Hamid Rezatofighi, Anton Milan, Javen Shi, Daniel Cremers, Ian Reid, Stefan Roth, Konrad Schindler, Laura Leal-Taixé

The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.

Computer Vision Multi-Object Tracking +2

Learn to Predict Sets Using Feed-Forward Neural Networks

no code implementations30 Jan 2020 Hamid Rezatofighi, Tianyu Zhu, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Anton Milan, Daniel Cremers, Laura Leal-Taixé, Ian Reid

In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality.

Multi-Label Image Classification object-detection +1

Learning a Neural Solver for Multiple Object Tracking

1 code implementation16 Dec 2019 Guillem Brasó, Laura Leal-Taixé

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm.

Multi-Object Tracking Multiple Object Tracking

HistoNet: Predicting size histograms of object instances

1 code implementation11 Dec 2019 Kishan Sharma, Moritz Gold, Christian Zurbruegg, Laura Leal-Taixé, Jan Dirk Wegner

Our method results in an overall improvement in the count and size distribution prediction as compared to state-of-the-art instance segmentation method Mask R-CNN.

Instance Segmentation Semantic Segmentation

Towards Generalizing Sensorimotor Control Across Weather Conditions

no code implementations25 Jul 2019 Qadeer Khan, Patrick Wenzel, Daniel Cremers, Laura Leal-Taixé

The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data.

Image-to-Image Translation Translation

Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation

13 code implementations23 Nov 2018 Mengyu Chu, You Xie, Jonas Mayer, Laura Leal-Taixé, Nils Thuerey

Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.

Image Super-Resolution Motion Compensation +3

Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs

1 code implementation3 Jul 2018 Patrick Wenzel, Qadeer Khan, Daniel Cremers, Laura Leal-Taixé

To this end, we propose to divide the task of vehicle control into two independent modules: a control module which is only trained on one weather condition for which labeled steering data is available, and a perception module which is used as an interface between new weather conditions and the fixed control module.

Self-Driving Cars

Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks

no code implementations ICLR 2019 S. Hamid Rezatofighi, Roman Kaskman, Farbod T. Motlagh, Qinfeng Shi, Daniel Cremers, Laura Leal-Taixé, Ian Reid

We demonstrate the validity of this new formulation on two relevant vision problems: object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO, and a complex CAPTCHA test, where we observe that, surprisingly, our set based network acquired the ability of mimicking arithmetics without any rules being coded.

object-detection Object Detection

Deep Appearance Maps

no code implementations ICCV 2019 Maxim Maximov, Laura Leal-Taixé, Mario Fritz, Tobias Ritschel

Second, we demonstrate how another network can be used to map from an image or video frames to a DAM network to reproduce this appearance, without using a lengthy optimization such as stochastic gradient descent (learning-to-learn).

Video Object Segmentation Without Temporal Information

no code implementations18 Sep 2017 Kevis-Kokitsi Maninis, Sergi Caelles, Yu-Hua Chen, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc van Gool

Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames.

Semantic Segmentation Semi-Supervised Video Object Segmentation +2

Fusion of Head and Full-Body Detectors for Multi-Object Tracking

no code implementations23 May 2017 Roberto Henschel, Laura Leal-Taixé, Daniel Cremers, Bodo Rosenhahn

In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach.

Multi-Object Tracking

Deep Depth From Focus

5 code implementations4 Apr 2017 Caner Hazirbas, Sebastian Georg Soyer, Maximilian Christian Staab, Laura Leal-Taixé, Daniel Cremers

Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision.

Computer Vision

One-Shot Video Object Segmentation

3 code implementations CVPR 2017 Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc van Gool

This paper tackles the task of semi-supervised video object segmentation, i. e., the separation of an object from the background in a video, given the mask of the first frame.

Semi-Supervised Video Object Segmentation Video Segmentation +1

Tracking with multi-level features

no code implementations25 Jul 2016 Roberto Henschel, Laura Leal-Taixé, Bodo Rosenhahn, Konrad Schindler

We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features.

Multiple Object Tracking

Learning by tracking: Siamese CNN for robust target association

no code implementations26 Apr 2016 Laura Leal-Taixé, Cristian Canton Ferrer, Konrad Schindler

This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections.

Multiple People Tracking Optical Flow Estimation

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

2 code implementations8 Apr 2015 Laura Leal-Taixé, Anton Milan, Ian Reid, Stefan Roth, Konrad Schindler

We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system.

3D Reconstruction Computer Vision +3

Multiple object tracking with context awareness

no code implementations24 Nov 2014 Laura Leal-Taixé

Multiple people tracking is a key problem for many applications such as surveillance, animation or car navigation, and a key input for tasks such as activity recognition.

Activity Recognition Multiple Object Tracking +1

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