Search Results for author:
Found 85 papers, 26 papers with code
BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects
In the new tasks, methods were required to learn new objects during a short onboarding stage (max 5 minutes, 1 GPU) from provided 3D object models.
ControlNet-XS: Designing an Efficient and Effective Architecture for Controlling Text-to-Image Diffusion Models
For this, a recent and highly popular approach is to use a controlling network, such as ControlNet, in combination with a pre-trained image generation model, such as Stable Diffusion.
Unsupervised Deep Graph Matching Based on Cycle Consistency
We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images.
Finding Competence Regions in Domain Generalization
We investigate a "learning to reject" framework to address the problem of silent failures in Domain Generalization (DG), where the test distribution differs from the training distribution.
BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects
In 2022, we witnessed another significant improvement in the pose estimation accuracy -- the state of the art, which was 56. 9 AR$_C$ in 2019 (Vidal et al.) and 69. 8 AR$_C$ in 2020 (CosyPose), moved to new heights of 83. 7 AR$_C$ (GDRNPP).
A Comparative Study of Graph Matching Algorithms in Computer Vision
To address these shortcomings, we present a comparative study of graph matching algorithms.
Towards Multimodal Depth Estimation from Light Fields
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.
Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networks
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.
Exoplanet Characterization using Conditional Invertible Neural Networks
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.
Neural Head Avatars from Monocular RGB Videos
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.
Self-Supervised Object Detection via Generative Image Synthesis
We present SSOD, the first end-to-end analysis-by synthesis framework with controllable GANs for the task of self-supervised object detection.
On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation
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
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.
Fusion Moves for Graph Matching
We contribute to approximate algorithms for the quadratic assignment problem also known as graph matching.
Benchmarking Invertible Architectures on Inverse Problems
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
One example is the registration of 2D X-ray images with preoperative three-dimensional computed tomography (CT) images in intraoperative surgical guidance systems.
Invertible Neural Networks for Uncertainty Quantification in Photoacoustic Imaging
Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation.
Learning Robust Models Using The Principle of Independent Causal Mechanisms
Standard supervised learning breaks down under data distribution shift.
Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers
With respect to our 16 different types of image corruptions and 5 different network backbones, we are in 74% better than training with clean data.
BOP Challenge 2020 on 6D Object Localization
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.
Generative Classifiers as a Basis for Trustworthy Image Classification
Generative classifiers (GCs) are a promising class of models that are said to naturally accomplish these qualities.
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
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.
Split-Merge Pooling
There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions.
Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimization
We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule.
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
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.
A Primal-Dual Solver for Large-Scale Tracking-by-Assignment
We demonstrate the efficacy of our method on real-world tracking problems.
Self-Supervised Viewpoint Learning From Image Collections
Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets.
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC
The framework consists of a deep neural network and fully differentiable pose optimization.
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
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.
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
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.
CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus
We present a robust estimator for fitting multiple parametric models of the same form to noisy measurements.
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
We address a core problem of computer vision: Detection and description of 2D feature points for image matching.
Out of distribution detection for intra-operative functional imaging
Multispectral optical imaging is becoming a key tool in the operating room.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Conditional Invertible Neural Networks for Guided Image Generation
In this work, we address the task of natural image generation guided by a conditioning input.
Learning to Think Outside the Box: Wide-Baseline Light Field Depth Estimation with EPI-Shift
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.
Benchmarking the Robustness of Semantic Segmentation Models
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.
Expert Sample Consensus Applied to Camera Re-Localization
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.
Guided Image Generation with Conditional Invertible Neural Networks
We demonstrate these properties for the tasks of MNIST digit generation and image colorization.
Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses
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.
Ranked #1 on
Horizon Line Estimation
on Horizon Lines in the Wild
Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
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
State of the art methods for semantic image segmentation are trained in a supervised fashion using a large corpus of fully labeled training images.
A Summary of the 4th International Workshop on Recovering 6D Object Pose
The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and an introduction of the BOP benchmark for 6D object pose estimation.
Geometric Image Synthesis
The task of generating natural images from 3D scenes has been a long standing goal in computer graphics.
BOP: Benchmark for 6D Object Pose Estimation
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image.
Analyzing Inverse Problems with Invertible Neural Networks
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.
Trust Your Model: Light Field Depth Estimation With Inline Occlusion Handling
We address the problem of depth estimation from light-field images.
Deep Object Co-Segmentation
This work presents a deep object co-segmentation (DOCS) approach for segmenting common objects of the same class within a pair of images.
Panoptic Segmentation
We propose and study a task we name panoptic segmentation (PS).
Ranked #23 on
Panoptic Segmentation
on Cityscapes val
(using extra training data)
iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects
We address the task of 6D pose estimation of known rigid objects from single input images in scenarios where the objects are partly occluded.
Learning Less is More - 6D Camera Localization via 3D Surface Regression
Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization.
Bounding Boxes, Segmentations and Object Coordinates: How Important Is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?
Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e. g., at texture-less or reflective surfaces.
Learning to Push the Limits of Efficient FFT-Based Image Deconvolution
This work addresses the task of non-blind image deconvolution.
Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes
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.
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
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.
Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
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.
Crowd Sourcing Image Segmentation with iaSTAPLE
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.
Detecting Unexpected Obstacles for Self-Driving Cars: Fusing Deep Learning and Geometric Modeling
To utilize the appearance and contextual cues, we propose a new deep learning-based obstacle detection framework.
A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching
We study the quadratic assignment problem, in computer vision also known as graph matching.
PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning
In this work we propose to learn an efficient algorithm for the task of 6D object pose estimation.
Global Hypothesis Generation for 6D Object Pose Estimation
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.
Implicit Modeling -- A Generalization of Discriminative and Generative Approaches
We propose a new modeling approach that is a generalization of generative and discriminative models.
InstanceCut: from Edges to Instances with MultiCut
This work addresses the task of instance-aware semantic segmentation.
DSAC - Differentiable RANSAC for Camera Localization
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.
Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications
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.
Can Ground Truth Label Propagation from Video help Semantic Segmentation?
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.
Random Forests versus Neural Networks - What's Best for Camera Localization?
This work addresses the task of camera localization in a known 3D scene given a single input RGB image.
Lost and Found: Detecting Small Road Hazards for Self-Driving Vehicles
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.
Stereo Video Deblurring
With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task.
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
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
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.
Reflection Modeling for Passive Stereo
Stereo reconstruction in presence of reality faces many challenges that still need to be addressed.
M-Best-Diverse Labelings for Submodular Energies and Beyond
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.
Inferring M-Best Diverse Labelings in a Single One
We consider the task of finding M-best diverse solutions in a graphical model.
Joint Training of Generic CNN-CRF Models with Stochastic Optimization
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.
Convexity Shape Constraints for Image Segmentation
Incorporating such prior knowledge into models and algorithms for image segmentation is highly desirable, yet can be non-trivial.
Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images
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.
Mapping Auto-context Decision Forests to Deep ConvNets for Semantic Segmentation
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.
Dense Semantic Image Segmentation with Objects and Attributes
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').
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs
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.
Cascades of Regression Tree Fields for Image Restoration
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.
A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems
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
Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image.
Discriminative Non-blind Deblurring
From this analysis, we derive a discriminative model cascade for image deblurring.
Depth Super Resolution by Rigid Body Self-Similarity in 3D
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.
Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance
We address the challenging task of decoupling material properties from lighting properties given a single image.
