Search Results for author: Carsten Rother

Found 79 papers, 23 papers with code

Towards Multimodal Depth Estimation from Light Fields

no code implementations30 Mar 2022 Titus Leistner, Radek Mackowiak, Lynton Ardizzone, Ullrich Köthe, Carsten Rother

We argue that this is due current methods only considering a single "true" depth, even when multiple objects at different depths contributed to the color of a single pixel.

Depth Estimation

Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networks

no code implementations18 Feb 2022 Haebom Lee, Christian Homeyer, Robert Herzog, Jan Rexilius, Carsten Rother

In this work, we focus on outdoor lighting estimation by aggregating individual noisy estimates from images, exploiting the rich image information from wide-angle cameras and/or temporal image sequences.

Camera Calibration Motion Estimation

Exoplanet Characterization using Conditional Invertible Neural Networks

no code implementations31 Jan 2022 Jonas Haldemann, Victor Ksoll, Daniel Walter, Yann Alibert, Ralf S. Klessen, Willy Benz, Ullrich Koethe, Lynton Ardizzone, Carsten Rother

Indeed, using cINNs allows for orders of magnitude faster inference of an exoplanet's composition than what is possible using an MCMC method, however, it still requires the computation of a large database of internal structures to train the cINN.

Bayesian Inference

Neural Head Avatars from Monocular RGB Videos

no code implementations2 Dec 2021 Philip-William Grassal, Malte Prinzler, Titus Leistner, Carsten Rother, Matthias Nießner, Justus Thies

We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human.

Novel View Synthesis

On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation

1 code implementation ICCV 2021 Eric Brachmann, Martin Humenberger, Carsten Rother, Torsten Sattler

This begs the question whether the choice of the reference algorithm favours a certain family of re-localisation methods.

Conditional Invertible Neural Networks for Diverse Image-to-Image Translation

1 code implementation5 May 2021 Lynton Ardizzone, Jakob Kruse, Carsten Lüth, Niels Bracher, Carsten Rother, Ullrich Köthe

We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images.

Colorization Image-to-Image Translation +1

Fusion Moves for Graph Matching

1 code implementation ICCV 2021 Lisa Hutschenreiter, Stefan Haller, Lorenz Feineis, Carsten Rother, Dagmar Kainmüller, Bogdan Savchynskyy

We contribute to approximate algorithms for the quadratic assignment problem also known as graph matching.

Graph Matching

Benchmarking Invertible Architectures on Inverse Problems

no code implementations26 Jan 2021 Jakob Kruse, Lynton Ardizzone, Carsten Rother, Ullrich Köthe

Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems.

Representing Ambiguity in Registration Problems with Conditional Invertible Neural Networks

no code implementations15 Dec 2020 Darya Trofimova, Tim Adler, Lisa Kausch, Lynton Ardizzone, Klaus Maier-Hein, Ulrich Köthe, Carsten Rother, Lena Maier-Hein

One example is the registration of 2D X-ray images with preoperative three-dimensional computed tomography (CT) images in intraoperative surgical guidance systems.

Computed Tomography (CT) Image Registration

Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging

no code implementations10 Nov 2020 Jan-Hinrich Nölke, Tim Adler, Janek Gröhl, Thomas Kirchner, Lynton Ardizzone, Carsten Rother, Ullrich Köthe, Lena Maier-Hein

Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation.

BOP Challenge 2020 on 6D Object Localization

3 code implementations15 Sep 2020 Tomas Hodan, Martin Sundermeyer, Bertram Drost, Yann Labbe, Eric Brachmann, Frank Michel, Carsten Rother, Jiri Matas

This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D image.

6D Pose Estimation 6D Pose Estimation using RGB +3

Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition

no code implementations29 Jun 2020 Hassan Abu Alhaija, Siva Karthik Mustikovela, Justus Thies, Varun Jampani, Matthias Nießner, Andreas Geiger, Carsten Rother

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process.

Image-to-Image Translation Intrinsic Image Decomposition +1

Split-Merge Pooling

no code implementations13 Jun 2020 Omid Hosseini Jafari, Carsten Rother

There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions.

Image Classification Semantic Segmentation

MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models

no code implementations ECCV 2018 Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications.

6D Pose Estimation using RGB

Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization

1 code implementation16 Apr 2020 Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule.

Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC

no code implementations27 Feb 2020 Eric Brachmann, Carsten Rother

The framework consists of a deep neural network and fully differentiable pose optimization.

Visual Localization

Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification

3 code implementations NeurIPS 2020 Lynton Ardizzone, Radek Mackowiak, Carsten Rother, Ullrich Köthe

In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information loss allows for an asymptotically exact formulation of the IB, while keeping the INN's generative capabilities intact.

General Classification Out-of-Distribution Detection

Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)

1 code implementation ICLR 2020 Peter Sorrenson, Carsten Rother, Ullrich Köthe

Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation.

Disentanglement

Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift

no code implementations19 Sep 2019 Titus Leistner, Hendrik Schilling, Radek Mackowiak, Stefan Gumhold, Carsten Rother

In order to work with wide-baseline light fields, we introduce the idea of EPI-Shift: To virtually shift the light field stack which enables to retain a small receptive field, independent of the disparity range.

Depth Estimation

Benchmarking the Robustness of Semantic Segmentation Models

no code implementations CVPR 2020 Christoph Kamann, Carsten Rother

When designing a semantic segmentation module for a practical application, such as autonomous driving, it is crucial to understand the robustness of the module with respect to a wide range of image corruptions.

Autonomous Driving General Classification +2

Expert Sample Consensus Applied to Camera Re-Localization

1 code implementation ICCV 2019 Eric Brachmann, Carsten Rother

In this work, we fit the 6D camera pose to a set of noisy correspondences between the 2D input image and a known 3D environment.

Camera Localization Visual Localization

Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses

3 code implementations ICCV 2019 Eric Brachmann, Carsten Rother

In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks.

Camera Localization Horizon Line Estimation +1

Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks

no code implementations8 Mar 2019 Tim J. Adler, Lynton Ardizzone, Anant Vemuri, Leonardo Ayala, Janek Gröhl, Thomas Kirchner, Sebastian Wirkert, Jakob Kruse, Carsten Rother, Ullrich Köthe, Lena Maier-Hein

Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed.

CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation

no code implementations23 Oct 2018 Radek Mackowiak, Philip Lenz, Omair Ghori, Ferran Diego, Oliver Lange, Carsten Rother

State of the art methods for semantic image segmentation are trained in a supervised fashion using a large corpus of fully labeled training images.

Active Learning Semantic Segmentation

Geometric Image Synthesis

no code implementations12 Sep 2018 Hassan Abu Alhaija, Siva Karthik Mustikovela, Andreas Geiger, Carsten Rother

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics.

Image Generation Instance Segmentation +1

Analyzing Inverse Problems with Invertible Neural Networks

2 code implementations ICLR 2019 Lynton Ardizzone, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, Ullrich Köthe

Often, the forward process from parameter- to measurement-space is a well-defined function, whereas the inverse problem is ambiguous: one measurement may map to multiple different sets of parameters.

Deep Object Co-Segmentation

2 code implementations17 Apr 2018 Weihao Li, Omid Hosseini jafari, Carsten Rother

This work presents a deep object co-segmentation (DOCS) approach for segmenting common objects of the same class within a pair of images.

iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects

no code implementations5 Dec 2017 Omid Hosseini Jafari, Siva Karthik Mustikovela, Karl Pertsch, Eric Brachmann, Carsten Rother

We address the task of 6D pose estimation of known rigid objects from single input images in scenarios where the objects are partly occluded.

6D Pose Estimation 6D Pose Estimation using RGB +2

Learning Less is More - 6D Camera Localization via 3D Surface Regression

1 code implementation CVPR 2018 Eric Brachmann, Carsten Rother

Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization.

Camera Localization Visual Localization

Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes

no code implementations4 Aug 2017 Hassan Abu Alhaija, Siva Karthik Mustikovela, Lars Mescheder, Andreas Geiger, Carsten Rother

Further, we demonstrate the utility of our approach on training standard deep models for semantic instance segmentation and object detection of cars in outdoor driving scenes.

Instance Segmentation Object Detection +1

Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation

no code implementations26 Feb 2017 Omid Hosseini Jafari, Oliver Groth, Alexander Kirillov, Michael Ying Yang, Carsten Rother

Towards this end we propose a Convolutional Neural Network (CNN) architecture that fuses the state of the state-of-the-art results for depth estimation and semantic labeling.

Depth Estimation Semantic Segmentation

Crowd Sourcing Image Segmentation with iaSTAPLE

no code implementations21 Feb 2017 Dmitrij Schlesinger, Florian Jug, Gene Myers, Carsten Rother, Dagmar Kainmüller

In an evaluation on a light microscopy dataset containing more than 5000 membrane labeled epithelial cells of a fly wing, we show that iaSTAPLE outperforms STAPLE in terms of segmentation accuracy as well as in terms of the accuracy of estimated crowd worker performance levels, and is able to correctly segment 99% of all cells when compared to expert segmentations.

Semantic Segmentation

Global Hypothesis Generation for 6D Object Pose Estimation

no code implementations CVPR 2017 Frank Michel, Alexander Kirillov, Eric Brachmann, Alexander Krull, Stefan Gumhold, Bogdan Savchynskyy, Carsten Rother

Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool.

6D Pose Estimation using RGB

DSAC - Differentiable RANSAC for Camera Localization

4 code implementations CVPR 2017 Eric Brachmann, Alexander Krull, Sebastian Nowozin, Jamie Shotton, Frank Michel, Stefan Gumhold, Carsten Rother

The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w. r. t.

Camera Localization Visual Localization

Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

1 code implementation14 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.

Combinatorial Optimization Multiple Object Tracking +2

Can Ground Truth Label Propagation from Video help Semantic Segmentation?

no code implementations3 Oct 2016 Siva Karthik Mustikovela, Michael Ying Yang, Carsten Rother

For state-of-the-art semantic segmentation task, training convolutional neural networks (CNNs) requires dense pixelwise ground truth (GT) labeling, which is expensive and involves extensive human effort.

Semantic Segmentation Video Segmentation +1

Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles

no code implementations15 Sep 2016 Peter Pinggera, Sebastian Ramos, Stefan Gehrig, Uwe Franke, Carsten Rother, Rudolf Mester

The proposed approach outperforms all considered baselines in our evaluations on both pixel and object level and runs at frame rates of up to 20 Hz on 2 mega-pixel stereo imagery.

Frame

Stereo Video Deblurring

no code implementations28 Jul 2016 Anita Sellent, Carsten Rother, Stefan Roth

With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task.

Deblurring

Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization

no code implementations NeurIPS 2016 Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of $\gamma$ in parallel, for certain diversity measures.

Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image

no code implementations CVPR 2016 Eric Brachmann, Frank Michel, Alexander Krull, Michael Ying Yang, Stefan Gumhold, Carsten Rother

In recent years, the task of estimating the 6D pose of object instances and complete scenes, i. e. camera localization, from a single input image has received considerable attention.

6D Pose Estimation 6D Pose Estimation using RGB +1

M-Best-Diverse Labelings for Submodular Energies and Beyond

no code implementations NeurIPS 2015 Alexander Kirillov, Dmytro Shlezinger, Dmitry P. Vetrov, Carsten Rother, Bogdan Savchynskyy

In this work we show that the joint inference of $M$ best diverse solutions can be formulated as a submodular energy minimization if the original MAP-inference problem is submodular, hence fast inference techniques can be used.

Total Energy

Reflection Modeling for Passive Stereo

no code implementations ICCV 2015 Rahul Nair, Andrew Fitzgibbon, Daniel Kondermann, Carsten Rother

Stereo reconstruction in presence of reality faces many challenges that still need to be addressed.

Joint Training of Generic CNN-CRF Models with Stochastic Optimization

no code implementations16 Nov 2015 Alexander Kirillov, Dmitrij Schlesinger, Shuai Zheng, Bogdan Savchynskyy, Philip H. S. Torr, Carsten Rother

We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters.

Stochastic Optimization

Convexity Shape Constraints for Image Segmentation

no code implementations CVPR 2016 Loic A. Royer, David L. Richmond, Carsten Rother, Bjoern Andres, Dagmar Kainmueller

Incorporating such prior knowledge into models and algorithms for image segmentation is highly desirable, yet can be non-trivial.

Semantic Segmentation

Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images

no code implementations ICCV 2015 Alexander Krull, Eric Brachmann, Frank Michel, Michael Ying Yang, Stefan Gumhold, Carsten Rother

This is done by describing the posterior density of a particular object pose with a convolutional neural network (CNN) that compares an observed and rendered image.

6D Pose Estimation 6D Pose Estimation using RGB

Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation

no code implementations27 Jul 2015 David L. Richmond, Dagmar Kainmueller, Michael Y. Yang, Eugene W. Myers, Carsten Rother

Finally, we revisit the core mapping from a Decision Tree (DT) to a NN, and show that it is also possible to map a fuzzy DT, with sigmoidal split decisions, to a NN.

Semantic Segmentation

Dense Semantic Image Segmentation with Objects and Attributes

no code implementations CVPR 2014 Shuai Zheng, Ming-Ming Cheng, Jonathan Warrell, Paul Sturgess, Vibhav Vineet, Carsten Rother, Philip H. S. Torr

The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e. g. "I see a shiny red chair').

Semantic Segmentation

SphereFlow: 6 DoF Scene Flow from RGB-D Pairs

no code implementations CVPR 2014 Michael Hornacek, Andrew Fitzgibbon, Carsten Rother

As a consequence of our approach, our output is a dense field of 3D rigid body motions, in contrast to the 3D translations that are the norm in scene flow.

Occlusion Handling

Cascades of Regression Tree Fields for Image Restoration

no code implementations8 Apr 2014 Uwe Schmidt, Jeremy Jancsary, Sebastian Nowozin, Stefan Roth, Carsten Rother

We posit two reasons for this: First, the blur kernel is often only known at test time, requiring any discriminative approach to cope with considerable variability.

Blind Image Deblurring Image Deblurring +2

A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems

no code implementations2 Apr 2014 Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy, Carsten Rother

However, on new and challenging types of models our findings disagree and suggest that polyhedral methods and integer programming solvers are competitive in terms of runtime and solution quality over a large range of model types.

Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation

no code implementations NeurIPS 2013 Vibhav Vineet, Carsten Rother, Philip Torr

Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image.

Depth Super Resolution by Rigid Body Self-Similarity in 3D

no code implementations CVPR 2013 Michael Hornacek, Christoph Rhemann, Margrit Gelautz, Carsten Rother

We tackle the problem of jointly increasing the spatial resolution and apparent measurement accuracy of an input low-resolution, noisy, and perhaps heavily quantized depth map.

Image Super-Resolution

Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance

no code implementations NeurIPS 2011 Carsten Rother, Martin Kiefel, Lumin Zhang, Bernhard Schölkopf, Peter V. Gehler

We address the challenging task of decoupling material properties from lighting properties given a single image.

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