Search Results for author: Friedrich Fraundorfer

Found 38 papers, 14 papers with code

HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans

2 code implementations12 Sep 2023 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automated and efficient approach for retrieving high-quality CAD models of objects and their poses in a scene captured by a moving RGB-D camera.

3D Object Retrieval 3D Scene Reconstruction +3

S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction

no code implementations ICCV 2023 Emanuele Santellani, Christian Sormann, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer

In this work we introduce S-TREK, a novel local feature extractor that combines a deep keypoint detector, which is both translation and rotation equivariant by design, with a lightweight deep descriptor extractor.

GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm

1 code implementation5 Jul 2023 Ludwig Mohr, Ismail Geles, Friedrich Fraundorfer

Rigid registration of point clouds is a fundamental problem in computer vision with many applications from 3D scene reconstruction to geometry capture and robotics.

3D Scene Reconstruction Graph Attention

Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing

no code implementations ICCV 2023 Stefano Zorzi, Friedrich Fraundorfer

Re:PolyWorld not only outperforms the original model on building extraction in aerial images, thanks to the proposed joint analysis of vertices and edges, but also beats the state-of-the-art in multiple other domains.

Instance Segmentation Scene Parsing +2

Automatically Annotating Indoor Images with CAD Models via RGB-D Scans

2 code implementations22 Dec 2022 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans.

3D Object Retrieval Pose Estimation +1

FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion

1 code implementation14 Sep 2022 Dominik Hirner, Friedrich Fraundorfer

This method extends FC-DCNN by improving the feature extractor, adding a network structure for training highly accurate similarity functions and a network structure for filling inconsistent disparity estimates.

Depth Completion

MD-Net: Multi-Detector for Local Feature Extraction

no code implementations10 Aug 2022 Emanuele Santellani, Christian Sormann, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer

In order to lower the computational cost of the matching phase, we propose a deep feature extraction network capable of detecting a predefined number of complementary sets of keypoints at each image.

3D Reconstruction

PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images

1 code implementation CVPR 2022 Stefano Zorzi, Shabab Bazrafkan, Stefan Habenschuss, Friedrich Fraundorfer

While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects instead of rasterized output.

Instance Segmentation Segmentation +1

Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks

no code implementations22 Nov 2021 Stefan Ainetter, Christoph Böhm, Rohit Dhakate, Stephan Weiss, Friedrich Fraundorfer

In this paper, we present a novel deep neural network architecture for joint class-agnostic object segmentation and grasp detection for robotic picking tasks using a parallel-plate gripper.

Instance Segmentation Object +3

End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB

1 code implementation12 Jul 2021 Stefan Ainetter, Friedrich Fraundorfer

In this work, we introduce a novel, end-to-end trainable CNN-based architecture to deliver high quality results for grasp detection suitable for a parallel-plate gripper, and semantic segmentation.

Robotic Grasping Segmentation +1

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

2 code implementations ICCV 2021 Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit

For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals.

BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo

no code implementations23 Oct 2020 Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn, Mattia Rossi, Thomas Pock, Friedrich Fraundorfer

We therefore show how we can calculate a normalization based on the expected 3D error, which we can then use to normalize the label jumps in the CRF.

FC-DCNN: A densely connected neural network for stereo estimation

3 code implementations14 Oct 2020 Dominik Hirner, Friedrich Fraundorfer

The output of this network is used in order to calculate matching costs and create a cost-volume.

Map-Repair: Deep Cadastre Maps Alignment and Temporal Inconsistencies Fix in Satellite Images

no code implementations24 Jul 2020 Stefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer

In the fast developing countries it is hard to trace new buildings construction or old structures destruction and, as a result, to keep the up-to-date cadastre maps.

Machine-learned Regularization and Polygonization of Building Segmentation Masks

no code implementations24 Jul 2020 Stefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer

We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks.

Generative Adversarial Network Segmentation

Regularization of Building Boundaries in Satellite Images using Adversarial and Regularized Losses

no code implementations23 Jul 2020 Stefano Zorzi, Friedrich Fraundorfer

In this paper we present a method for building boundary refinement and regularization in satellite images using a fully convolutional neural network trained with a combination of adversarial and regularized losses.

Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems

1 code implementation13 Mar 2020 Patrick Knöbelreiter, Christian Sormann, Alexander Shekhovtsov, Friedrich Fraundorfer, Thomas Pock

It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models.

Optical Flow Estimation Semantic Segmentation

General 3D Room Layout from a Single View by Render-and-Compare

1 code implementation ECCV 2020 Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit

In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate.

Minimal Solutions for Relative Pose with a Single Affine Correspondence

no code implementations CVPR 2020 Banglei Guan, Ji Zhao, Zhang Li, Fang Sun, Friedrich Fraundorfer

In this paper we present four cases of minimal solutions for two-view relative pose estimation by exploiting the affine transformation between feature points and we demonstrate efficient solvers for these cases.

Motion Estimation Outlier Detection +1

Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning

no code implementations29 Apr 2019 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision.

Semantic Segmentation

S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation

no code implementations27 Dec 2018 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views.

Segmentation Semi-Supervised Semantic Segmentation

Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization

no code implementations ECCV 2018 Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof

We propose a method for urban 3D reconstruction, which incorporates semantic information and plane priors within the reconstruction process in order to generate visually appealing 3D models.

3D Reconstruction

Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks

no code implementations14 Aug 2018 Muhammad Shahzad, Michael Maurer, Friedrich Fraundorfer, Yuanyuan Wang, Xiao Xiang Zhu

This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high resolution (VHR) synthetic aperture radar (SAR) images.

General Classification Image Classification

Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems

no code implementations9 May 2018 Georg Waltner, Michael Maurer, Thomas Holzmann, Patrick Ruprecht, Michael Opitz, Horst Possegger, Friedrich Fraundorfer, Horst Bischof

Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems.

3D Object Classification Classification +2

Evaluation of CNN-based Single-Image Depth Estimation Methods

no code implementations3 May 2018 Tobias Koch, Lukas Liebel, Friedrich Fraundorfer, Marco Körner

While an increasing interest in deep models for single-image depth estimation methods can be observed, established schemes for their evaluation are still limited.

Depth Estimation

Prioritized Multi-View Stereo Depth Map Generation Using Confidence Prediction

no code implementations22 Mar 2018 Christian Mostegel, Friedrich Fraundorfer, Horst Bischof

In the second step, we rank the resulting view clusters (i. e. key views with matching partners) according to their impact on the fulfillment of desired quality parameters such as completeness, ground resolution and accuracy.

3D Reconstruction

Deep learning in remote sensing: a review

1 code implementation11 Oct 2017 Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, Friedrich Fraundorfer

In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with.

Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity

no code implementations CVPR 2017 Christian Mostegel, Rudolf Prettenthaler, Friedrich Fraundorfer, Horst Bischof

In this paper we present a scalable approach for robustly computing a 3D surface mesh from multi-scale multi-view stereo point clouds that can handle extreme jumps of point density (in our experiments three orders of magnitude).

Surface Reconstruction

UAV-based Autonomous Image Acquisition with Multi-View Stereo Quality Assurance by Confidence Prediction

no code implementations6 May 2016 Christian Mostegel, Markus Rumpler, Friedrich Fraundorfer, Horst Bischof

In this paper we present an autonomous system for acquiring close-range high-resolution images that maximize the quality of a later-on 3D reconstruction with respect to coverage, ground resolution and 3D uncertainty.

3D Reconstruction

Using Self-Contradiction to Learn Confidence Measures in Stereo Vision

no code implementations CVPR 2016 Christian Mostegel, Markus Rumpler, Friedrich Fraundorfer, Horst Bischof

Learned confidence measures gain increasing importance for outlier removal and quality improvement in stereo vision.

Relative Pose Estimation for a Multi-Camera System with Known Vertical Direction

no code implementations CVPR 2014 Gim Hee Lee, Marc Pollefeys, Friedrich Fraundorfer

In this paper, we present our minimal 4-point and linear 8-point algorithms to estimate the relative pose of a multi-camera system with known vertical directions, i. e. known absolute roll and pitch angles.

Pose Estimation

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