Search Results for author:
Found 225 papers, 95 papers with code
Relative Volume Constraints for Single View 3D Reconstruction
We introduce the concept of relative volume constraints in order to account for insufficient information in the reconstruction of 3D objects from a single image.
Co-Sparse Textural Similarity for Image Segmentation
We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation within a convex multilabel optimization framework.
Dense Non-Rigid Shape Correspondence using Random Forests
We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations.
Sequential Convex Relaxation for Mutual Information-Based Unsupervised Figure-Ground Segmentation
We propose an optimization algorithm for mutual-information-based unsupervised figure-ground separation.
The Primal-Dual Hybrid Gradient Method for Semiconvex Splittings
This paper deals with the analysis of a recent reformulation of the primal-dual hybrid gradient method [Zhu and Chan 2008, Pock, Cremers, Bischof and Chambolle 2009, Esser, Zhang and Chan 2010, Chambolle and Pock 2011], which allows to apply it to nonconvex regularizers as first proposed for truncated quadratic penalization in [Strekalovskiy and Cremers 2014].
Variational Depth from Focus Reconstruction
This paper deals with the problem of reconstructing a depth map from a sequence of differently focused images, also known as depth from focus or shape from focus.
FlowNet: Learning Optical Flow with Convolutional Networks
Optical flow estimation has not been among the tasks where CNNs were successful.
Adopting an Unconstrained Ray Model in Light-Field Cameras for 3D Shape Reconstruction
This results in several drawbacks, ranging from the difficulties in feature detection, due to the reduced size of each microlens, to the need to adopt a model with a relatively small number of parameters.
Partial Functional Correspondence
In this paper, we propose a method for computing partial functional correspondence between non-rigid shapes.
Point-wise Map Recovery and Refinement from Functional Correspondence
Since their introduction in the shape analysis community, functional maps have met with considerable success due to their ability to compactly represent dense correspondences between deformable shapes, with applications ranging from shape matching and image segmentation, to exploration of large shape collections.
Collaborative Total Variation: A General Framework for Vectorial TV Models
Even after over two decades, the total variation (TV) remains one of the most popular regularizations for image processing problems and has sparked a tremendous amount of research, particularly to move from scalar to vector-valued functions.
Dense Continuous-Time Tracking and Mapping With Rolling Shutter RGB-D Cameras
Using a continuous trajectory representation has a number of advantages over a discrete-time representation (e. g. camera poses at the frame interval).
Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations
In this paper, we show how to perform model-based object tracking which allows to reconstruct the object's depth at an order of magnitude higher frame-rate through simple modifications to an off-the-shelf depth camera.
Entropy Minimization for Convex Relaxation Approaches
Despite their enormous success in solving hard combinatorial problems, convex relaxation approaches often suffer from the fact that the computed solutions are far from binary and that subsequent heuristic binarization may substantially degrade the quality of computed solutions.
Learning Nonlinear Spectral Filters for Color Image Reconstruction
This paper presents the idea of learning optimal filters for color image reconstruction based on a novel concept of nonlinear spectral image decompositions recently proposed by Guy Gilboa.
Sublabel-Accurate Relaxation of Nonconvex Energies
We propose a novel spatially continuous framework for convex relaxations based on functional lifting.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
Efficient Globally Optimal 2D-to-3D Deformable Shape Matching
We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a 3D shape represented as a surface; the output is a continuous curve on the surface.
Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies
Convex relaxations of nonconvex multilabel problems have been demonstrated to produce superior (provably optimal or near-optimal) solutions to a variety of classical computer vision problems.
A Photometrically Calibrated Benchmark For Monocular Visual Odometry
We present a dataset for evaluating the tracking accuracy of monocular visual odometry and SLAM methods.
Bayesian Inference of Bijective Non-Rigid Shape Correspondence
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.
From Monocular SLAM to Autonomous Drone Exploration
Micro aerial vehicles (MAVs) are strongly limited in their payload and power capacity.
De-noising, Stabilizing and Completing 3D Reconstructions On-the-go using Plane Priors
Our implementation is optimized to run in real-time on mobile devices such as the Tango tablet.
A Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching
We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data.
One-Shot Video Object Segmentation
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.
Sublabel-Accurate Discretization of Nonconvex Free-Discontinuity Problems
In this work we show how sublabel-accurate multilabeling approaches can be derived by approximating a classical label-continuous convex relaxation of nonconvex free-discontinuity problems.
Multiframe Motion Coupling for Video Super Resolution
The idea of video super resolution is to use different view points of a single scene to enhance the overall resolution and quality.
Image-based localization using LSTMs for structured feature correlation
In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes.
Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images
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.
Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks
We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces.
Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space
Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space.
Real-Time Trajectory Replanning for MAVs using Uniform B-splines and a 3D Circular Buffer
In this paper, we present a real-time approach to local trajectory replanning for microaerial vehicles (MAVs).
Robotics
Nonlinear Spectral Image Fusion
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks.
Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras
At test time, the semantics predictions of our network can be fused more consistently in semantic keyframe maps than predictions of a network trained on individual views.
Dense Multi-view 3D-reconstruction Without Dense Correspondences
We introduce a variational method for multi-view shape-from-shading under natural illumination.
Deep Depth From Focus
Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision.
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Standardized benchmarks are crucial for the majority of computer vision applications.
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks.
3D Deep Learning for Biological Function Prediction from Physical Fields
In this paper, we show that deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields.
Challenges in Monocular Visual Odometry: Photometric Calibration, Motion Bias and Rolling Shutter Effect
Monocular visual odometry (VO) and simultaneous localization and mapping (SLAM) have seen tremendous improvements in accuracy, robustness and efficiency, and have gained increasing popularity over recent years.
Monocular Visual Odometry
Simultaneous Localization and Mapping
Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier.
Fusion of Head and Full-Body Detectors for Multi-Object Tracking
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach.
Ranked #21 on
Multi-Object Tracking
on MOT16
Learning by Association - A versatile semi-supervised training method for neural networks
We demonstrate the capabilities of learning by association on several data sets and show that it can improve performance on classification tasks tremendously by making use of additionally available unlabeled data.
Proximal Backpropagation
Specifically, we show that backpropagation of a prediction error is equivalent to sequential gradient descent steps on a quadratic penalty energy, which comprises the network activations as variables of the optimization.
A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting
This paper tackles the photometric stereo problem in the presence of inaccurate lighting, obtained either by calibration or by an uncalibrated photometric stereo method.
An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models
We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views.
Learning by Association -- A Versatile Semi-Supervised Training Method for Neural Networks
We demonstrate the capabilities of learning by association on several data sets and show that it can improve performance on classification tasks tremendously by making use of additionally available unlabeled data.
KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences
We introduce a geometry-driven approach for real-time 3D reconstruction of deforming surfaces from a single RGB-D stream without any templates or shape priors.
LED-based Photometric Stereo: Modeling, Calibration and Numerical Solution
The second one directly recovers the depth, by formulating photometric stereo as a system of PDEs which are partially linearized using image ratios.
Efficient Deformable Shape Correspondence via Kernel Matching
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality.
Depth Super-Resolution Meets Uncalibrated Photometric Stereo
A novel depth super-resolution approach for RGB-D sensors is presented.
Associative Domain Adaptation
Our training scheme follows the paradigm that in order to effectively derive class labels for the target domain, a network should produce statistically domain invariant embeddings, while minimizing the classification error on the labeled source domain.
Ranked #6 on
Domain Adaptation
on SYNSIG-to-GTSRB
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
We introduce a novel method to obtain high-quality 3D reconstructions from consumer RGB-D sensors.
Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras
We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras.
Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction
State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously updating the reconstructed surface on pose changes.
Video Object Segmentation Without Temporal Information
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.
Variational Reflectance Estimation from Multi-view Images
We tackle the problem of reflectance estimation from a set of multi-view images, assuming known geometry.
A Variational Approach to Shape-from-shading Under Natural Illumination
A numerical solution to shape-from-shading under natural illumination is presented.
Online Photometric Calibration for Auto Exposure Video for Realtime Visual Odometry and SLAM
We further show that our calibration can improve the performance of a state-of-the-art direct visual odometry method that works solely on pixel intensities, calibrating for photometric parameters in an online fashion in realtime.
Regularization for Deep Learning: A Taxonomy
Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other.
Combinatorial Preconditioners for Proximal Algorithms on Graphs
We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners.
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
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.
Clustering with Deep Learning: Taxonomy and New Methods
In this paper, we propose a systematic taxonomy of clustering methods that utilize deep neural networks.
Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization
We present VI-DSO, a novel approach for visual-inertial odometry, which jointly estimates camera poses and sparse scene geometry by minimizing photometric and IMU measurement errors in a combined energy functional.
The TUM VI Benchmark for Evaluating Visual-Inertial Odometry
For trajectory evaluation, we also provide accurate pose ground truth from a motion capture system at high frequency (120 Hz) at the start and end of the sequences which we accurately aligned with the camera and IMU measurements.
Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks
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.
Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From Shading
We put forward a principled variational approach for up-sampling a single depth map to the resolution of the companion color image provided by an RGB-D sensor.
q-Space Novelty Detection with Variational Autoencoders
Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regularizer; and that abnormal samples differ from normal samples not only in input-feature space, but also in the VAE latent space and VAE output.
Divergence-Free Shape Interpolation and Correspondence
We present a novel method to model and calculate deformation fields between shapes embedded in $\mathbb{R}^D$.
Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs
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.
A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking
We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects using a monocular RGB camera.
Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry
To this end, we incorporate deep depth predictions into Direct Sparse Odometry (DSO) as direct virtual stereo measurements.
The Double Sphere Camera Model
We evaluate the model using a calibration dataset with several different lenses and compare the models using the metrics that are relevant for Visual Odometry, i. e., reprojection error, as well as computation time for projection and unprojection functions and their Jacobians.
Direct Sparse Odometry with Rolling Shutter
Neglecting the effects of rolling-shutter cameras for visual odometry (VO) severely degrades accuracy and robustness.
LDSO: Direct Sparse Odometry with Loop Closure
In this paper we present an extension of Direct Sparse Odometry (DSO) to a monocular visual SLAM system with loop closure detection and pose-graph optimization (LDSO).
Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform
Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs).
Omnidirectional DSO: Direct Sparse Odometry with Fisheye Cameras
We propose a novel real-time direct monocular visual odometry for omnidirectional cameras.
DeepWrinkles: Accurate and Realistic Clothing Modeling
We present a novel method to generate accurate and realistic clothing deformation from real data capture.
MRF Optimization with Separable Convex Prior on Partially Ordered Labels
To this end, we assume that the label set is the Cartesian product of totally ordered sets and the convex prior is separable.
Photometric Depth Super-Resolution
This study explores the use of photometric techniques (shape-from-shading and uncalibrated photometric stereo) for upsampling the low-resolution depth map from an RGB-D sensor to the higher resolution of the companion RGB image.
Probabilistic Discriminative Learning with Layered Graphical Models
Probabilistic graphical models are traditionally known for their successes in generative modeling.
Homogeneous Linear Inequality Constraints for Neural Network Activations
One way to achieve this task is by means of a projection step at test time after unconstrained training.
Optimization of Inf-Convolution Regularized Nonconvex Composite Problems
In this work, we consider nonconvex composite problems that involve inf-convolution with a Legendre function, which gives rise to an anisotropic generalization of the proximal mapping and Moreau-envelope.
Controlling Neural Networks via Energy Dissipation
The last decade has shown a tremendous success in solving various computer vision problems with the help of deep learning techniques.
Variational Uncalibrated Photometric Stereo under General Lighting
Photometric stereo (PS) techniques nowadays remain constrained to an ideal laboratory setup where modeling and calibration of lighting is amenable.
Visual-Inertial Mapping with Non-Linear Factor Recovery
We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO.
DirectShape: Direct Photometric Alignment of Shape Priors for Visual Vehicle Pose and Shape Estimation
Scene understanding from images is a challenging problem encountered in autonomous driving.
GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization
Direct SLAM methods have shown exceptional performance on odometry tasks.
Lifting Vectorial Variational Problems: A Natural Formulation based on Geometric Measure Theory and Discrete Exterior Calculus
Numerous tasks in imaging and vision can be formulated as variational problems over vector-valued maps.
Learning to Evolve
Here we show that learning to evolve, i. e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness.
Flat Metric Minimization with Applications in Generative Modeling
We take the novel perspective to view data not as a probability distribution but rather as a current.
Smooth Shells: Multi-Scale Shape Registration with Functional Maps
Smooth shells define a series of coarse-to-fine shape approximations designed to work well with multiscale algorithms.
CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision applications.
Towards Generalizing Sensorimotor Control Across Weather Conditions
The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data.
Sparse Surface Constraints for Combining Physics-based Elasticity Simulation and Correspondence-Free Object Reconstruction
In a number of tests using synthetic datasets and real-world measurements, we analyse the robustness of our approach and the convergence behavior of the numerical optimization scheme.
Graphics I.6
Bregman Proximal Framework for Deep Linear Neural Networks
This initiated the development of the Bregman proximal gradient (BPG) algorithm and an inertial variant (momentum based) CoCaIn BPG, which however rely on problem dependent Bregman distances.
Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light
We propose the concept of a multi-frame GAN (MFGAN) and demonstrate its potential as an image sequence enhancement for stereo visual odometry in low light conditions.
Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods
Convolutional networks are successful due to their equivariance/invariance under translations.
Rolling-Shutter Modelling for Direct Visual-Inertial Odometry
The visual part of the system performs a photometric bundle adjustment on a sparse set of points.
On the well-posedness of uncalibrated photometric stereo under general lighting
While the theoretical foundations of this inverse problem under directional lighting are well-established, there is a lack of mathematical evidence for the uniqueness of a solution under general lighting.
Efficient Derivative Computation for Cumulative B-Splines on Lie Groups
Continuous-time trajectory representation has recently gained popularity for tasks where the fusion of high-frame-rate sensors and multiple unsynchronized devices is required.
Informative GANs via Structured Regularization of Optimal Transport
We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT).
Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach
A novel approach towards depth map super-resolution using multi-view uncalibrated photometric stereo is presented.
From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds
We propose a new method for segmentation-free joint estimation of orthogonal planes, their intersection lines, relationship graph and corners lying at the intersection of three orthogonal planes.
Learn to Predict Sets Using Feed-Forward Neural Networks
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.
Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning
Structured convex optimization on weighted graphs finds numerous applications in machine learning and computer vision.
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation.
MOT20: A benchmark for multi object tracking in crowded scenes
The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+2
Hamiltonian Dynamics for Real-World Shape Interpolation
While most prior work focuses on synthetic input shapes, our formulation is designed to be applicable to real-world scans with imperfect input correspondences and various types of noise.
PrimiTect: Fast Continuous Hough Voting for Primitive Detection
This paper tackles the problem of data abstraction in the context of 3D point sets.
Effective Version Space Reduction for Convolutional Neural Networks
In active learning, sampling bias could pose a serious inconsistency problem and hinder the algorithm from finding the optimal hypothesis.
Ranked #108 on
Image Classification
on STL-10
Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost Functions
Computer-aided drug discovery is an essential component of modern drug development.
A Chain Graph Interpretation of Real-World Neural Networks
It is thus a promising framework that deepens our understanding of neural networks and provides a coherent theoretical formulation for future deep learning research.
DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
We generate the global descriptor by directly aggregating the learned local descriptors with an effective attention mechanism.
Ranked #7 on
3D Place Recognition
on Oxford RobotCar Dataset
4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving
We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving.
LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization
The learned features significantly improve the robustness of direct image alignment, especially for relocalization across different conditions.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
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.
Unsupervised Dense Shape Correspondence using Heat Kernels
In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework.
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network.
MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
Unlike other multi-view stereo methods, MonoRec is able to reconstruct both static and moving objects by leveraging the predicted masks.
SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors.
Ranked #5 on
3D Place Recognition
on Oxford RobotCar Dataset
(AR@1% metric)
Non-Rigid Puzzles
We assume to be given a reference shape and its multiple parts undergoing a non-rigid deformation.
i3DMM: Deep Implicit 3D Morphable Model of Human Heads
Our approach has the following favorable properties: (i) It is the first full head morphable model that includes hair.
Isometric Multi-Shape Matching
Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer.
Post-hoc Uncertainty Calibration for Domain Drift Scenarios
First, we show that existing post-hoc calibration methods yield highly over-confident predictions under domain shift.
Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry
To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely on feature matching to associate online visual odometry (VO) with a previously built map.
Rotation-Equivariant Deep Learning for Diffusion MRI
So far, they have been proposed for 2D and 3D data.
Variational Data Assimilation with a Learned Inverse Observation Operator
Variational data assimilation optimizes for an initial state of a dynamical system such that its evolution fits observational data.
STEP: Segmenting and Tracking Every Pixel
The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation.
Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration
We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS).
Square Root Bundle Adjustment for Large-Scale Reconstruction
We propose a new formulation for the bundle adjustment problem which relies on nullspace marginalization of landmark variables by QR decomposition.
Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
Obstacle avoidance is a fundamental and challenging problem for autonomous navigation of mobile robots.
Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry
Vision-based learning methods for self-driving cars have primarily used supervised approaches that require a large number of labels for training.
Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
While these approaches mainly focus on learning node and edge attributes, they completely ignore the 3D geometry of the underlying 3D objects depicted in the 2D images.
Ranked #11 on
Graph Matching
on PASCAL VOC
DeepLab2: A TensorFlow Library for Deep Labeling
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision.
NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i. e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them.
Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization
We propose a novel method for continuous-time feature tracking in event cameras.
Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields
In contrast to existing discretizations which suffer from a grid bias, we show that a piecewise polynomial discretization better preserves the continuous nature of our problem.
Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification
To learn the direct influence among output nodes in a graph, we propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.
TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset
The event cameras contain a large sensor of 1280x720 pixels, which is significantly larger than the sensors used in existing stereo event datasets (at least by a factor of ten).
Dive into Layers: Neural Network Capacity Bounding using Algebraic Geometry
To mathematically prove this, we borrow a tool in topological algebra: Betti numbers to measure the topological geometric complexity of input data and the neural network.
Square Root Marginalization for Sliding-Window Bundle Adjustment
The square root formulation pervades three major aspects of our optimization-based sliding-window estimator: for bundle adjustment we eliminate landmark variables with nullspace projection; to store the marginalization prior we employ a matrix square root of the Hessian; and when marginalizing old poses we avoid forming normal equations and update the square root prior directly with a specialized QR decomposition.
Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions
In contrast to most other approaches, our framework can also handle rotation-only motions that are particularly challenging for monocular odometry systems.
Scene Graph Generation for Better Image Captioning?
We investigate the incorporation of visual relationships into the task of supervised image caption generation by proposing a model that leverages detected objects and auto-generated visual relationships to describe images in natural language.
Scalable Sinkhorn Backpropagation
Our main contribution is deriving a simple and efficient algorithm that performs this backward pass in closed form.
Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation
We address the non-convex optimisation problem of finding a sparse matrix on the Stiefel manifold (matrices with mutually orthogonal columns of unit length) that maximises (or minimises) a quadratic objective function.
Multidirectional Conjugate Gradients for Scalable Bundle Adjustment
We revisit the problem of large-scale bundle adjustment and propose a technique called Multidirectional Conjugate Gradients that accelerates the solution of the normal equation by up to 61%.
TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo
In this paper, we present TANDEM a real-time monocular tracking and dense mapping framework.
Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction
We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations.
Shortest Paths in Graphs with Matrix-Valued Edges: Concepts, Algorithm and Application to 3D Multi-Shape Analysis
Traditionally, the concept of a shortest path is considered for graphs with scalar edge weights, which makes it possible to compute the length of a path by adding up the individual edge weights.
DM-VIO: Delayed Marginalization Visual-Inertial Odometry
This is the foundation of the proposed pose graph bundle adjustment, which we use for IMU initialization.
Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications
In this paper, we present a complete pipeline for 3D semantic mapping solely based on a stereo camera system.
Intrinsic Neural Fields: Learning Functions on Manifolds
Neural fields have gained significant attention in the computer vision community due to their excellent performance in novel view synthesis, geometry reconstruction, and generative modeling.
Lateral Ego-Vehicle Control without Supervision using Point Clouds
In this paper, a framework for training a more robust and scalable model for lateral vehicle control is proposed.
DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes.
FIRe: Fast Inverse Rendering using Directional and Signed Distance Functions
To this end, we learn a signed distance function (SDF) along with our DDF model to represent a class of shapes.
The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions
However, their approach does not take into account uncertainties, so that the accuracy of the estimated relative pose is highly dependent on accurate feature positions in the target frame.
Implicit Shape Completion via Adversarial Shape Priors
Finally, we show that our adversarial training approach leads to visually plausible reconstructions that are highly consistent in recovering missing parts of a given object.
A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching
We present a scalable combinatorial algorithm for globally optimizing over the space of geometrically consistent mappings between 3D shapes.
Power Bundle Adjustment for Large-Scale 3D Reconstruction
We demonstrate that employing the proposed Power Bundle Adjustment as a sub-problem solver significantly improves speed and accuracy of the distributed optimization.
Neural Implicit Representations for Physical Parameter Inference from a Single Video
Neural networks have recently been used to analyze diverse physical systems and to identify the underlying dynamics.
A Unified Framework for Implicit Sinkhorn Differentiation
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.
VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environments
Visual Place Recognition and Visual Localization are essential components in navigation and mapping for autonomous vehicles especially in GNSS-denied navigation scenarios.
CHALLENGER: Training with Attribution Maps
Regularization is key in deep learning, especially when training complex models on relatively small datasets.
Biologically Inspired Neural Path Finding
The human brain can be considered to be a graphical structure comprising of tens of billions of biological neurons connected by synapses.
Efficient and Flexible Sublabel-Accurate Energy Minimization
While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias.
Semantic Self-adaptation: Enhancing Generalization with a Single Sample
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation.
E-NeRF: Neural Radiance Fields from a Moving Event Camera
We also show that combining events and frames can overcome failure cases of NeRF estimation in scenarios where only a few input views are available without requiring additional regularization.
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
Direct methods have shown excellent performance in the applications of visual odometry and SLAM.
What Makes Graph Neural Networks Miscalibrated?
Furthermore, based on the insights from this study, we design a novel calibration method named Graph Attention Temperature Scaling (GATS), which is tailored for calibrating graph neural networks.
Deep Combinatorial Aggregation
In this work, we explore a combinatorial generalization of deep ensemble called deep combinatorial aggregation (DCA).
High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF
Fine-detailed reconstructions are in high demand in many applications.
A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs
Current graph neural networks (GNNs) that tackle node classification on graphs tend to only focus on nodewise scores and are solely evaluated by nodewise metrics.
CASSPR: Cross Attention Single Scan Place Recognition
CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the output global descriptor of the point cloud.
PRISM: Probabilistic Real-Time Inference in Spatial World Models
We introduce PRISM, a method for real-time filtering in a probabilistic generative model of agent motion and visual perception.
G-MSM: Unsupervised Multi-Shape Matching with Graph-based Affinity Priors
We present G-MSM (Graph-based Multi-Shape Matching), a novel unsupervised learning approach for non-rigid shape correspondence.
SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering
We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3D shape and material parameters from a set of color images in a super-resolution manner.
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
The models pretrained with MEM are also label-efficient and generalize well to the dense task of semantic image segmentation.
4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions
In this paper, we present a novel visual SLAM and long-term localization benchmark for autonomous driving in challenging conditions based on the large-scale 4Seasons dataset.
DDIT: Semantic Scene Completion via Deformable Deep Implicit Templates
It abstracts the shape prior of a category, and thus can provide constraints on the overall shape of an instance.
Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information
This is done by training a neural network which takes the state and intent of the multiple vehicles to predict their future trajectory.
Behind the Scenes: Density Fields for Single View Reconstruction
By directly sampling color from the available views instead of storing color in the density field, our scene representation becomes significantly less complex compared to NeRFs, and a neural network can predict it in a single forward pass.
Semidefinite Relaxations for Robust Multiview Triangulation
We propose an approach based on convex relaxations for certifiably optimal robust multiview triangulation.
Beyond In-Domain Scenarios: Robust Density-Aware Calibration
While existing post-hoc calibration methods achieve impressive results on in-domain test datasets, they are limited by their inability to yield reliable uncertainty estimates in domain-shift and out-of-domain (OOD) scenarios.
Scale-Equivariant Deep Learning for 3D Data
The ability of convolutional neural networks (CNNs) to recognize objects regardless of their position in the image is due to the translation-equivariance of the convolutional operation.
Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks
To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts.
Joint MR sequence optimization beats pure neural network approaches for spin-echo MRI super-resolution
The found radiofrequency pulse train designs generate an optimal signal for the NN to perform the SR task.
Non-Separable Multi-Dimensional Network Flows for Visual Computing
Flows in networks (or graphs) play a significant role in numerous computer vision tasks.
Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes
Moreover, we employ an unsupervised latent exploration algorithm in the $\mathcal{S}$-space of the generator and show that it is more efficient than the conventional $\mathcal{W}^{+}$-space in controlling the image content.
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
We propose a differentiable nonlinear least squares framework to account for uncertainty in relative pose estimation from feature correspondences.
Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations
Neural implicits have become popular for representing surfaces because they offer an adaptive resolution and support arbitrary topologies.
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks.
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events.
LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels
We train a deep learning model, which takes a LiDAR scan as input and predicts the future trajectory as output.
Neural Poisson Surface Reconstruction: Resolution-Agnostic Shape Reconstruction from Point Clouds
Overall, the neural Poisson surface reconstruction not only improves upon the limitations of classical deep neural networks in shape reconstruction but also achieves superior results in terms of reconstruction quality, running time, and resolution agnosticism.
SIGMA: Scale-Invariant Global Sparse Shape Matching
We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for highly non-rigid shapes.
Robust Autonomous Vehicle Pursuit without Expert Steering Labels
In this work, we present a learning method for lateral and longitudinal motion control of an ego-vehicle for vehicle pursuit.
Deep Video Codec Control for Vision Models
To overcome the deterioration of vision performance, this paper presents the first end-to-end learnable deep video codec control that considers both bandwidth constraints and downstream deep vision performance, while adhering to existing standardization.
