
NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go
We present NeuroMorph, a new neural network architecture that takes as i...
read it

Joint Deep MultiGraph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections
Graph matching aims to establish correspondences between vertices of gra...
read it

SelfSupervised Steering Angle Prediction for Vehicle Control Using Visual Odometry
Visionbased learning methods for selfdriving cars have primarily used ...
read it

VisionBased Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
Obstacle avoidance is a fundamental and challenging problem for autonomo...
read it

Square Root Bundle Adjustment for LargeScale Reconstruction
We propose a new formulation for the bundle adjustment problem which rel...
read it

Parameterized Temperature Scaling for Boosting the Expressive Power in PostHoc Uncertainty Calibration
We address the problem of uncertainty calibration and introduce a novel ...
read it

STEP: Segmenting and Tracking Every Pixel
In this paper, we tackle video panoptic segmentation, a task that requir...
read it

Variational Data Assimilation with a Learned Inverse Observation Operator
Variational data assimilation optimizes for an initial state of a dynami...
read it

RotationEquivariant Deep Learning for Diffusion MRI
Convolutional networks are successful, but they have recently been outpe...
read it

Tight Integration of FeatureBased Relocalization in Monocular Direct Visual Odometry
In this paper we propose a framework for integrating mapbased relocaliz...
read it

Posthoc Uncertainty Calibration for Domain Drift Scenarios
We address the problem of uncertainty calibration. While standard deep n...
read it

Neural Online Graph Exploration
Can we learn how to explore unknown spaces efficiently? To answer this q...
read it

Isometric MultiShape Matching
Finding correspondences between shapes is a fundamental problem in compu...
read it

i3DMM: Deep Implicit 3D Morphable Model of Human Heads
We present the first deep implicit 3D morphable model (i3DMM) of full he...
read it

NonRigid Puzzles
Shape correspondence is a fundamental problem in computer graphics and v...
read it

SOENet: A SelfAttention and Orientation Encoding Network for Point Cloud based Place Recognition
We tackle the problem of place recognition from point cloud data and int...
read it

MonoRec: SemiSupervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
In this paper, we propose MonoRec, a semisupervised monocular dense rec...
read it

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
We propose a novel unsupervised learning approach to 3D shape correspond...
read it

Speech Synthesis and Control Using Differentiable DSP
Modern texttospeech systems are able to produce natural and highquali...
read it

Unsupervised Dense Shape Correspondence using Heat Kernels
In this work, we propose an unsupervised method for learning dense corre...
read it

MOTChallenge: A Benchmark for Singlecamera Multiple Target Tracking
Standardized benchmarks have been crucial in pushing the performance of ...
read it

LMReloc: LevenbergMarquardt Based Direct Visual Relocalization
We present LMReloc – a novel approach for visual relocalization based o...
read it

4Seasons: A CrossSeason Dataset for MultiWeather SLAM in Autonomous Driving
We present a novel dataset covering seasonal and challenging perceptual ...
read it

DH3D: Deep Hierarchical 3D Descriptors for Robust LargeScale 6DoF Relocalization
For relocalization in largescale point clouds, we propose the first app...
read it

Deriving Neural Network Design and Learning from the Probabilistic Framework of Chain Graphs
The last decade has witnessed a boom of neural network (NN) research and...
read it

Effective Version Space Reduction for Convolutional Neural Networks
In active learning, sampling bias could pose a serious inconsistency pro...
read it

PrimiTect: Fast Continuous Hough Voting for Primitive Detection
This paper tackles the problem of data abstraction in the context of 3D ...
read it

Hamiltonian Dynamics for RealWorld Shape Interpolation
We revisit the classical problem of 3D shape interpolation and propose a...
read it

MOT20: A benchmark for multi object tracking in crowded scenes
Standardized benchmarks are crucial for the majority of computer vision ...
read it

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
We propose D3VO as a novel framework for monocular visual odometry that ...
read it

Optimization of Graph Total Variation via ActiveSetbased Combinatorial Reconditioning
Structured convex optimization on weighted graphs finds numerous applica...
read it

Learn to Predict Sets Using FeedForward Neural Networks
This paper addresses the task of set prediction using deep feedforward ...
read it

From Planes to Corners: MultiPurpose Primitive Detection in Unorganized 3D Point Clouds
We propose a new method for segmentationfree joint estimation of orthog...
read it

Inferring SuperResolution Depth from a Moving LightSource Enhanced RGBD Sensor: A Variational Approach
A novel approach towards depth map superresolution using multiview unc...
read it

Informative GANs via Structured Regularization of Optimal Transport
We tackle the challenge of disentangled representation learning in gener...
read it

Efficient Derivative Computation for Cumulative BSplines on Lie Groups
Continuoustime trajectory representation has recently gained popularity...
read it

On the wellposedness of uncalibrated photometric stereo under general lighting
Uncalibrated photometric stereo aims at estimating the 3Dshape of a sur...
read it

RollingShutter Modelling for Direct VisualInertial Odometry
We present a direct visualinertial odometry (VIO) method which estimate...
read it

Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods
One of the reasons for the success of convolutional networks is their eq...
read it

MultiFrame GAN: Image Enhancement for Stereo Visual Odometry in Low Light
We propose the concept of a multiframe GAN (MFGAN) and demonstrate its ...
read it

Bregman Proximal Framework for Deep Linear Neural Networks
A typical assumption for the analysis of first order optimization method...
read it

Sparse Surface Constraints for Combining Physicsbased Elasticity Simulation and CorrespondenceFree Object Reconstruction
We address the problem to infer physical material parameters and boundar...
read it

Lifting methods for manifoldvalued variational problems
Lifting methods allow to transform hard variational problems such as seg...
read it

Towards Generalizing Sensorimotor Control Across Weather Conditions
The ability of deep learning models to generalize well across different ...
read it

CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision ...
read it

Smooth Shells: MultiScale Shape Registration with Functional Maps
We propose a novel 3D shape correspondence method based on the iterative...
read it

Flat Metric Minimization with Applications in Generative Modeling
We take the novel perspective to view data not as a probability distribu...
read it

Learning to Evolve
Evolution and learning are two of the fundamental mechanisms by which li...
read it

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 pr...
read it

GNNet: The GaussNewton Loss for Deep Direct SLAM
Direct methods for SLAM have shown exceptional performance on odometry t...
read it