no code implementations • 11 Apr 2024 • Simon Schrodi, David T. Hoffmann, Max Argus, Volker Fischer, Thomas Brox
This revealed that the driving factor behind both, the modality gap and the object bias, is the information imbalance between images and captions.
no code implementations • 22 Mar 2024 • Nick Heppert, Max Argus, Tim Welschehold, Thomas Brox, Abhinav Valada
Subsequently, in the live online trajectory generation stage, we first \mbox{re-detect} all objects, then we warp the demonstration trajectory to the current scene, and finally, we trace the trajectory with the robot.
no code implementations • 21 Mar 2024 • Baohe Zhang, Yuan Zhang, Lilli Frison, Thomas Brox, Joschka Bödecker
However, for many real-world problems, it is often more convenient to formulate optimization problems in terms of rewards and constraints simultaneously.
1 code implementation • 11 Feb 2024 • Simon Ging, María A. Bravo, Thomas Brox
The evaluation of text-generative vision-language models is a challenging yet crucial endeavor.
Ranked #1 on Visual Question Answering (VQA) on ActivityNet
Open Vocabulary Attribute Detection Visual Question Answering
1 code implementation • 5 Feb 2024 • Riccardo Grazzi, Julien Siems, Simon Schrodi, Thomas Brox, Frank Hutter
State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual information provided as input to the model.
1 code implementation • 21 Dec 2023 • Philipp Schröppel, Christopher Wewer, Jan Eric Lenssen, Eddy Ilg, Thomas Brox
However, none of the existing models enable disentangled generation to control the shape and appearance separately.
no code implementations • 13 Nov 2023 • Maximilian Luz, Rohit Mohan, Ahmed Rida Sekkat, Oliver Sawade, Elmar Matthes, Thomas Brox, Abhinav Valada
Optical flow estimation is very challenging in situations with transparent or occluded objects.
no code implementations • 19 Oct 2023 • David T. Hoffmann, Simon Schrodi, Nadine Behrmann, Volker Fischer, Thomas Brox
In this work, we study rapid, step-wise improvements of the loss in transformers when being confronted with multi-step decision tasks.
no code implementations • 10 Oct 2023 • Karim Farid, Simon Schrodi, Max Argus, Thomas Brox
LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation and focus on the important, semantic parts of the data.
1 code implementation • 9 Oct 2023 • Simon Schrodi, Ferdinand Briegel, Max Argus, Andreas Christen, Thomas Brox
We show the efficacy of our approach across a wide spectrum of study areas and time scales.
no code implementations • 6 Oct 2023 • Max Argus, Abhijeet Nayak, Martin Büchner, Silvio Galesso, Abhinav Valada, Thomas Brox
In this work, we present a framework that formulates the visual servoing task as graph traversal.
no code implementations • ICCV 2023 • Ke Fan, Zechen Bai, Tianjun Xiao, Dominik Zietlow, Max Horn, Zixu Zhao, Carl-Johann Simon-Gabriel, Mike Zheng Shou, Francesco Locatello, Bernt Schiele, Thomas Brox, Zheng Zhang, Yanwei Fu, Tong He
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization.
1 code implementation • ICCV 2023 • Zixu Zhao, Jiaze Wang, Max Horn, Yizhuo Ding, Tong He, Zechen Bai, Dominik Zietlow, Carl-Johann Simon-Gabriel, Bing Shuai, Zhuowen Tu, Thomas Brox, Bernt Schiele, Yanwei Fu, Francesco Locatello, Zheng Zhang, Tianjun Xiao
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
1 code implementation • 25 May 2023 • Arian Mousakhan, Thomas Brox, Jawad Tayyub
In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD), a novel denoising process for image reconstruction conditioned on a target image.
Ranked #2 on Anomaly Detection on MVTec AD
no code implementations • 8 Feb 2023 • Sudhanshu Mittal, Joshua Niemeijer, Jörg P. Schäfer, Thomas Brox
Active learning is particularly of interest for semantic segmentation, where annotations are costly.
1 code implementation • CVPR 2023 • María A. Bravo, Sudhanshu Mittal, Simon Ging, Thomas Brox
The objective of the novel task and benchmark is to probe object-level attribute information learned by vision-language models.
1 code implementation • 12 Nov 2022 • Silvio Galesso, Max Argus, Thomas Brox
In this paper, we show that nearest-neighbor approaches also yield state-of-the-art results on dense novelty detection in complex driving scenes when working with an appropriate feature representation.
Ranked #1 on Anomaly Detection on Fishyscapes L&F (using extra training data)
2 code implementations • NeurIPS 2023 • Simon Schrodi, Danny Stoll, Binxin Ru, Rhea Sukthanker, Thomas Brox, Frank Hutter
In this work, we introduce a unifying search space design framework based on context-free grammars that can naturally and compactly generate expressive hierarchical search spaces that are 100s of orders of magnitude larger than common spaces from the literature.
3 code implementations • 29 Sep 2022 • Maximilian Seitzer, Max Horn, Andrii Zadaianchuk, Dominik Zietlow, Tianjun Xiao, Carl-Johann Simon-Gabriel, Tong He, Zheng Zhang, Bernhard Schölkopf, Thomas Brox, Francesco Locatello
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
1 code implementation • 18 Sep 2022 • Leonhard Sommer, Philipp Schröppel, Thomas Brox
SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation.
1 code implementation • 13 Sep 2022 • Philipp Schröppel, Jan Bechtold, Artemij Amiranashvili, Thomas Brox
We show that recent approaches do not generalize across datasets in this setting.
1 code implementation • 30 Aug 2022 • Silvio Galesso, Maria Alejandra Bravo, Mehdi Naouar, Thomas Brox
Detection of out-of-distribution (OoD) samples in the context of image classification has recently become an area of interest and active study, along with the topic of uncertainty estimation, to which it is closely related.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
1 code implementation • 19 Jul 2022 • Florian Wenzel, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, Chris Russell, Thomas Brox, Bernt Schiele, Bernhard Schölkopf, Francesco Locatello
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e. g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations.
Adversarial Robustness Out-of-Distribution Generalization +1
1 code implementation • 11 Jul 2022 • Andrii Zadaianchuk, Matthaeus Kleindessner, Yi Zhu, Francesco Locatello, Thomas Brox
In this paper, we show that recent advances in self-supervised feature learning enable unsupervised object discovery and semantic segmentation with a performance that matches the state of the field on supervised semantic segmentation 10 years ago.
no code implementations • 8 Jul 2022 • Yash Sharma, Yi Zhu, Chris Russell, Thomas Brox
While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision.
no code implementations • 17 May 2022 • Sergio Izquierdo, Max Argus, Thomas Brox
Visual Servoing has been effectively used to move a robot into specific target locations or to track a recorded demonstration.
1 code implementation • 12 May 2022 • Maria A. Bravo, Sudhanshu Mittal, Thomas Brox
In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes.
no code implementations • 10 Apr 2022 • Gabriel Kalweit, Maria Kalweit, Mansour Alyahyay, Zoe Jaeckel, Florian Steenbergen, Stefanie Hardung, Thomas Brox, Ilka Diester, Joschka Boedecker
However, since generally there is a strong connection between learning of subjects and their expectations on long-term rewards, we propose NeuRL, an inverse reinforcement learning approach that (1) extracts an intrinsic reward function from collected trajectories of a subject in closed form, (2) maps neural signals to this intrinsic reward to account for long-term dependencies in the behavior and (3) predicts the simulated behavior for unseen neural signals by extracting Q-values and the corresponding Boltzmann policy based on the intrinsic reward values for these unseen neural signals.
no code implementations • 15 Feb 2022 • Thomas Elsken, Arber Zela, Jan Hendrik Metzen, Benedikt Staffler, Thomas Brox, Abhinav Valada, Frank Hutter
The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering.
1 code implementation • 27 Jan 2022 • David T. Hoffmann, Nadine Behrmann, Juergen Gall, Thomas Brox, Mehdi Noroozi
This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples.
1 code implementation • 16 Dec 2021 • Estibaliz Gómez-de-Mariscal, Hasini Jayatilaka, Özgün Çiçek, Thomas Brox, Denis Wirtz, Arrate Muñoz-Barrutia
Studying cell morphology changes in time is critical to understanding cell migration mechanisms.
1 code implementation • 13 Oct 2021 • Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling.
no code implementations • ICLR 2022 • Osama Makansi, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Dominik Janzing, Thomas Brox, Bernhard Schölkopf
Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions.
no code implementations • ICCV 2021 • Mohammadreza Zolfaghari, Yi Zhu, Peter Gehler, Thomas Brox
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples.
no code implementations • 9 Jul 2021 • Ashwin Raaghav Narayanan, Arber Zela, Tonmoy Saikia, Thomas Brox, Frank Hutter
Ensembles of CNN models trained with different seeds (also known as Deep Ensembles) are known to achieve superior performance over a single copy of the CNN.
no code implementations • 28 Jun 2021 • Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach, Evgeny Levinkov, Thomas Brox, Jan Hendrik Metzen
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
18 code implementations • CVPR 2022 • Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler
Being able to spot defective parts is a critical component in large-scale industrial manufacturing.
Ranked #3 on Anomaly Detection on AeBAD-V
no code implementations • 8 Jun 2021 • Christian Zimmermann, Max Argus, Thomas Brox
This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning.
no code implementations • 1 Jun 2021 • Julia Guerrero-Viu, Sergio Izquierdo, Philipp Schröppel, Thomas Brox
Despite the success of deep learning in disparity estimation, the domain generalization gap remains an issue.
no code implementations • NeurIPS 2021 • Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach, Evgeny Levinkov, Thomas Brox, Jan Hendrik Metzen
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
no code implementations • 29 Apr 2021 • Artemij Amiranashvili, Max Argus, Lukas Hermann, Wolfram Burgard, Thomas Brox
Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots.
no code implementations • CVPR 2021 • Jan Bechtold, Maxim Tatarchenko, Volker Fischer, Thomas Brox
Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training.
1 code implementation • CVPR 2022 • Simon Schrodi, Tonmoy Saikia, Thomas Brox
We show how these mistakes can be rectified in order to make optical flow networks robust to physical patch-based attacks.
no code implementations • ICCV 2021 • Tonmoy Saikia, Cordelia Schmid, Thomas Brox
CNNs perform remarkably well when the training and test distributions are i. i. d, but unseen image corruptions can cause a surprisingly large drop in performance.
1 code implementation • ICCV 2021 • Osama Makansi, Özgün Cicek, Yassine Marrakchi, Thomas Brox
Predicting the states of dynamic traffic actors into the future is important for autonomous systems to operate safelyand efficiently.
1 code implementation • 18 Feb 2021 • Sudhanshu Mittal, Silvio Galesso, Thomas Brox
Contemporary neural networks are limited in their ability to learn from evolving streams of training data.
1 code implementation • 20 Nov 2020 • Özgün Çiçek, Yassine Marrakchi, Enoch Boasiako Antwi, Barbara Di Ventura, Thomas Brox
In this paper, we provide a solution to segmentation of imperfect data through time based on temporal propagation and uncertainty estimation.
1 code implementation • NeurIPS 2020 • Simon Ging, Mohammadreza Zolfaghari, Hamed Pirsiavash, Thomas Brox
Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics.
Ranked #4 on Video Captioning on ActivityNet Captions
no code implementations • 19 Jul 2020 • Gabriel L. Oliveira, Senthil Yogamani, Wolfram Burgard, Thomas Brox
In order to further improve the architecture we introduce a weight function which aims to re-balance classes to increase the attention of the networks to under-represented objects.
1 code implementation • 6 Jul 2020 • Artemij Amiranashvili, Nicolai Dorka, Wolfram Burgard, Vladlen Koltun, Thomas Brox
Imitation learning is a powerful family of techniques for learning sensorimotor coordination in immersive environments.
no code implementations • 1 Jul 2020 • Max Argus, Lukas Hermann, Jon Long, Thomas Brox
One-shot imitation is the vision of robot programming from a single demonstration, rather than by tedious construction of computer code.
no code implementations • 14 Jun 2020 • Andong Tan, Duc Tam Nguyen, Maximilian Dax, Matthias Nießner, Thomas Brox
Self-attention networks have shown remarkable progress in computer vision tasks such as image classification.
1 code implementation • CVPR 2020 • Osama Makansi, Özgün Cicek, Kevin Buchicchio, Thomas Brox
In this paper, we investigate the problem of anticipating future dynamics, particularly the future location of other vehicles and pedestrians, in the view of a moving vehicle.
1 code implementation • 4 Apr 2020 • Andres Munoz, Mohammadreza Zolfaghari, Max Argus, Thomas Brox
In this paper, we present a network architecture for video generation that models spatio-temporal consistency without resorting to costly 3D architectures.
no code implementations • 22 Jan 2020 • Tonmoy Saikia, Thomas Brox, Cordelia Schmid
To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning.
no code implementations • 11 Dec 2019 • Sudhanshu Mittal, Maxim Tatarchenko, Özgün Çiçek, Thomas Brox
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples.
no code implementations • NeurIPS 2019 • Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
1 code implementation • 17 Oct 2019 • Oier Mees, Maxim Tatarchenko, Thomas Brox, Wolfram Burgard
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image.
3D Object Reconstruction From A Single Image 3D Reconstruction +3
1 code implementation • 17 Oct 2019 • Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards.
no code implementations • ICLR 2020 • Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, Thomas Brox
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time.
no code implementations • 28 Sep 2019 • Duc Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
no code implementations • 25 Sep 2019 • Aditya Bhatt, Max Argus, Artemij Amiranashvili, Thomas Brox
Off-policy temporal difference (TD) methods are a powerful class of reinforcement learning (RL) algorithms.
1 code implementation • ICLR 2020 • Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, Frank Hutter
Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of the resulting bi-level optimization problem.
no code implementations • ICCV 2019 • Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox
We show that methods trained on our dataset consistently perform well when tested on other datasets.
Ranked #8 on 3D Hand Pose Estimation on FreiHAND
1 code implementation • 15 Aug 2019 • Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox
The ability to understand visual information from limited labeled data is an important aspect of machine learning.
no code implementations • 9 Aug 2019 • Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
1 code implementation • CVPR 2019 • Osama Makansi, Eddy Ilg, Özgün Cicek, Thomas Brox
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers.
no code implementations • 1 Jun 2019 • Duc Tam Nguyen, Thi-Phuong-Nhung Ngo, Zhongyu Lou, Michael Klar, Laura Beggel, Thomas Brox
We consider the problem of training a model under the presence of label noise.
1 code implementation • ICCV 2019 • Tonmoy Saikia, Yassine Marrakchi, Arber Zela, Frank Hutter, Thomas Brox
In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures.
no code implementations • CVPR 2019 • Maxim Tatarchenko, Stephan R. Richter, René Ranftl, Zhuwen Li, Vladlen Koltun, Thomas Brox
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research.
Ranked #1 on 3D Reconstruction on 300W
1 code implementation • 9 May 2019 • Mohammadreza Zolfaghari, Özgün Çiçek, Syed Mohsin Ali, Farzaneh Mahdisoltani, Can Zhang, Thomas Brox
Foreseeing the future is one of the key factors of intelligence.
2 code implementations • ICLR 2019 • Duc Tam Nguyen, Zhongyu Lou, Michael Klar, Thomas Brox
Thus, due to the lack of representative data, the wide-spread discriminative approaches cannot cover such learning tasks, and rather generative models, which attempt to learn the input density of the normal cases, are used.
no code implementations • 11 Apr 2019 • Juan Leon Alcazar, Maria A. Bravo, Ali K. Thabet, Guillaume Jeanneret, Thomas Brox, Pablo Arbelaez, Bernard Ghanem
Instance-level video segmentation requires a solid integration of spatial and temporal information.
1 code implementation • CVPR 2019 • Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model.
3 code implementations • 14 Feb 2019 • Aditya Bhatt, Daniel Palenicek, Boris Belousov, Max Argus, Artemij Amiranashvili, Thomas Brox, Jan Peters
Sample efficiency is a crucial problem in deep reinforcement learning.
no code implementations • 10 Jan 2019 • Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox
In dynamic environments, learned controllers are supposed to take motion into account when selecting the action to be taken.
no code implementations • ICCV 2019 • Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space.
2 code implementations • ICLR 2019 • Duc Tam Nguyen, Zhongyu Lou, Michael Klar, Thomas Brox
In one-class-learning tasks, only the normal case (foreground) can be modeled with data, whereas the variation of all possible anomalies is too erratic to be described by samples.
no code implementations • 20 Aug 2018 • Osama Makansi, Eddy Ilg, Thomas Brox
The latter can be used as proxy-ground-truth to train a network on real-world data and to adapt it to specific domains of interest.
1 code implementation • ECCV 2018 • Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
For mapping, we accumulate information in a cost volume centered at the current depth estimate.
1 code implementation • ECCV 2018 • Eddy Ilg, Tonmoy Saikia, Margret Keuper, Thomas Brox
Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
1 code implementation • ICLR 2018 • Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox
Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators.
6 code implementations • ECCV 2018 • Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox
In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time.
Ranked #65 on Action Recognition on Something-Something V1
1 code implementation • 7 Mar 2018 • Christian Zimmermann, Tim Welschehold, Christian Dornhege, Wolfram Burgard, Thomas Brox
We propose an approach to estimate 3D human pose in real world units from a single RGBD image and show that it exceeds performance of monocular 3D pose estimation approaches from color as well as pose estimation exclusively from depth.
Ranked #14 on 3D Human Pose Estimation on Total Capture
1 code implementation • ECCV 2018 • Eddy Ilg, Özgün Çiçek, Silvio Galesso, Aaron Klein, Osama Makansi, Frank Hutter, Thomas Brox
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology.
1 code implementation • 19 Jan 2018 • Nikolaus Mayer, Eddy Ilg, Philipp Fischer, Caner Hazirbas, Daniel Cremers, Alexey Dosovitskiy, Thomas Brox
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations.
1 code implementation • 22 Aug 2017 • Jonas Uhrig, Nick Schneider, Lukas Schneider, Uwe Franke, Thomas Brox, Andreas Geiger
In this paper, we consider convolutional neural networks operating on sparse inputs with an application to depth upsampling from sparse laser scan data.
Ranked #16 on Depth Completion on KITTI Depth Completion
4 code implementations • 13 Aug 2017 • Manuel Ruder, Alexey Dosovitskiy, Thomas Brox
We propose a deep network architecture and training procedures that allow us to stylize arbitrary-length videos in a consistent and stable way, and nearly in real time.
no code implementations • 3 Jul 2017 • Osama Makansi, Eddy Ilg, Thomas Brox
We analyze the usage of optical flow for video super-resolution and find that common off-the-shelf image warping does not allow video super-resolution to benefit much from optical flow.
no code implementations • CVPR 2017 • Evgeny Levinkov, Jonas Uhrig, Siyu Tang, Mohamed Omran, Eldar Insafutdinov, Alexander Kirillov, Carsten Rother, Thomas Brox, Bernt Schiele, Bjoern Andres
In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time.
no code implementations • 27 Jun 2017 • Gabriel L. Oliveira, Noha Radwan, Wolfram Burgard, Thomas Brox
Compared to LiDAR-based localization methods, which provide high accuracy but rely on expensive sensors, visual localization approaches only require a camera and thus are more cost-effective while their accuracy and reliability typically is inferior to LiDAR-based methods.
8 code implementations • ICCV 2017 • Christian Zimmermann, Thomas Brox
Low-cost consumer depth cameras and deep learning have enabled reasonable 3D hand pose estimation from single depth images.
no code implementations • ICCV 2017 • Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, Volker Fischer
We show empirically that there exist barely perceptible universal noise patterns which result in nearly the same predicted segmentation for arbitrary inputs.
1 code implementation • ICCV 2017 • Mohammadreza Zolfaghari, Gabriel L. Oliveira, Nima Sedaghat, Thomas Brox
In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images.
4 code implementations • 28 Mar 2017 • Anna Khoreva, Rodrigo Benenson, Eddy Ilg, Thomas Brox, Bernt Schiele
Our approach is suitable for both single and multiple object segmentation.
1 code implementation • ICCV 2017 • Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation.
Ranked #3 on 3D Reconstruction on Data3D−R2N2
no code implementations • 3 Mar 2017 • Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox
Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations.
no code implementations • 12 Dec 2016 • Nima Sedaghat, Mohammadreza Zolfaghari, Thomas Brox
With the help of a sample-variant multi-tasking architecture, the network is trained on different tasks depending on the availability of ground-truth.
2 code implementations • CVPR 2017 • Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig, Nikolaus Mayer, Eddy Ilg, Alexey Dosovitskiy, Thomas Brox
In this paper we formulate structure from motion as a learning problem.
12 code implementations • CVPR 2017 • Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, Thomas Brox
Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods.
Dense Pixel Correspondence Estimation Optical Flow Estimation +1
no code implementations • NeurIPS 2016 • Vladimir Golkov, Marcin J. Skwark, Antonij Golkov, Alexey Dosovitskiy, Thomas Brox, Jens Meiler, Daniel Cremers
A contact map is a compact representation of the three-dimensional structure of a protein via the pairwise contacts between the amino acid constituting the protein.
1 code implementation • 14 Nov 2016 • Evgeny Levinkov, Jonas Uhrig, Siyu Tang, Mohamed Omran, Eldar Insafutdinov, Alexander Kirillov, Carsten Rother, Thomas Brox, Bernt Schiele, Bjoern Andres
In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time.
no code implementations • 10 Aug 2016 • Benjamin Drayer, Thomas Brox
In contrast to most tracking methods, it provides an accurate, temporally consistent segmentation of each object.
no code implementations • 21 Jul 2016 • Margret Keuper, Siyu Tang, Yu Zhongjie, Bjoern Andres, Thomas Brox, Bernt Schiele
Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios.
27 code implementations • 21 Jun 2016 • Özgün Çiçek, Ahmed Abdulkadir, Soeren S. Lienkamp, Thomas Brox, Olaf Ronneberger
This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images.
Ranked #27 on 3D Instance Segmentation on ScanNet(v2)
no code implementations • 8 Jun 2016 • Margret Keuper, Thomas Brox
In this paper, we tackle the problem of temporally consistent boundary detection and hierarchical segmentation in videos.
5 code implementations • NeurIPS 2016 • Anh Nguyen, Alexey Dosovitskiy, Jason Yosinski, Thomas Brox, Jeff Clune
Understanding the inner workings of such computational brains is both fascinating basic science that is interesting in its own right - similar to why we study the human brain - and will enable researchers to further improve DNNs.
3 code implementations • 28 Apr 2016 • Manuel Ruder, Alexey Dosovitskiy, Thomas Brox
We present an approach that transfers the style from one image (for example, a painting) to a whole video sequence.
no code implementations • 18 Apr 2016 • Jonas Uhrig, Marius Cordts, Uwe Franke, Thomas Brox
Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models.
no code implementations • 12 Apr 2016 • Nima Sedaghat, Mohammadreza Zolfaghari, Ehsan Amiri, Thomas Brox
In this paper, we show that the object orientation plays an important role in 3D recognition.
Ranked #2 on 3D Object Classification on ModelNet10
10 code implementations • NeurIPS 2016 • Alexey Dosovitskiy, Thomas Brox
This metric better reflects perceptually similarity of images and thus leads to better results.
3 code implementations • CVPR 2016 • Nikolaus Mayer, Eddy Ilg, Philip Häusser, Philipp Fischer, Daniel Cremers, Alexey Dosovitskiy, Thomas Brox
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
no code implementations • ICCV 2015 • Naveen Shankar Nagaraja, Frank R. Schmidt, Thomas Brox
As the use of videos is becoming more popular in computer vision, the need for annotated video datasets increases.
no code implementations • ICCV 2015 • Margret Keuper, Bjoern Andres, Thomas Brox
For the segmentation of moving objects in videos, the analysis of long-term point trajectories has been very popular recently.
no code implementations • ICCV 2015 • Benjamin Ummenhofer, Thomas Brox
We present a variational approach for surface reconstruction from a set of oriented points with scale information.
no code implementations • ICCV 2015 • Nima Sedaghat, Thomas Brox
Object recognition approaches have recently been extended to yield, aside of the object class output, also viewpoint or pose.
no code implementations • 20 Nov 2015 • Maxim Tatarchenko, Alexey Dosovitskiy, Thomas Brox
We present a convolutional network capable of inferring a 3D representation of a previously unseen object given a single image of this object.
2 code implementations • CVPR 2016 • Alexey Dosovitskiy, Thomas Brox
Inverting a deep network trained on ImageNet provides several insights into the properties of the feature representation learned by the network.
1 code implementation • CVPR 2015 • Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox
We train a generative convolutional neural network which is able to generate images of objects given object type, viewpoint, and color.
no code implementations • ICCV 2015 • Margret Keuper, Evgeny Levinkov, Nicolas Bonneel, Guillaume Lavoué, Thomas Brox, Bjoern Andres
a pixel grid graph have received little attention, firstly, because the MP is NP-hard and instances w. r. t.
477 code implementations • 18 May 2015 • Olaf Ronneberger, Philipp Fischer, Thomas Brox
There is large consent that successful training of deep networks requires many thousand annotated training samples.
Ranked #1 on Semantic Segmentation on STARE
18 code implementations • ICCV 2015 • Philipp Fischer, Alexey Dosovitskiy, Eddy Ilg, Philip Häusser, Caner Hazırbaş, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, Thomas Brox
Optical flow estimation has not been among the tasks where CNNs were successful.
37 code implementations • 21 Dec 2014 • Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller
Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers.
Ranked #117 on Image Classification on CIFAR-10
no code implementations • NeurIPS 2014 • Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox
Current methods for training convolutional neural networks depend on large amounts of labeled samples for supervised training.
Ranked #84 on Image Classification on STL-10
2 code implementations • 21 Nov 2014 • Alexey Dosovitskiy, Jost Tobias Springenberg, Maxim Tatarchenko, Thomas Brox
We train generative 'up-convolutional' neural networks which are able to generate images of objects given object style, viewpoint, and color.
1 code implementation • 26 Jun 2014 • Alexey Dosovitskiy, Philipp Fischer, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox
While such generic features cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor.
no code implementations • CVPR 2014 • Fabio Galasso, Margret Keuper, Thomas Brox, Bernt Schiele
In contrast to previous work, the reduced graph is reweighted such that the resulting segmentation is equivalent, under certain assumptions, to that of the full graph.
no code implementations • 22 May 2014 • Philipp Fischer, Alexey Dosovitskiy, Thomas Brox
Surprisingly, convolutional neural networks clearly outperform SIFT on descriptor matching.
no code implementations • 18 Apr 2014 • Peter Ochs, Yunjin Chen, Thomas Brox, Thomas Pock
A rigorous analysis of the algorithm for the proposed class of problems yields global convergence of the function values and the arguments.
no code implementations • 18 Dec 2013 • Alexey Dosovitskiy, Jost Tobias Springenberg, Thomas Brox
We then extend these trivial one-element classes by applying a variety of transformations to the initial 'seed' patches.
no code implementations • CVPR 2013 • Peter Ochs, Alexey Dosovitskiy, Thomas Brox, Thomas Pock
Here we extend the problem class to linearly constrained optimization of a Lipschitz continuous function, which is the sum of a convex function and a function being concave and increasing on the non-negative orthant (possibly non-convex and nonconcave on the whole space).
no code implementations • CVPR 2013 • Margret Keuper, Thorsten Schmidt, Maja Temerinac-Ott, Jan Padeken, Patrick Heun, Olaf Ronneberger, Thomas Brox
With volumetric data from widefield fluorescence microscopy, many emerging questions in biological and biomedical research are being investigated.