3.2k citations · 3.3k across the 27 of their papers we have counts for
36 papers
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer +1
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. We first investigate…
S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction
Emanuele Santellani, Christian Sormann, Mattia Rossi +2
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 light…
GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm
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. If a suitable i…
Automatically Annotating Indoor Images with CAD Models via RGB-D Scans
Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer +1
We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans. Through a visual evaluation by 3D experts, we sh…
DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo
Christian Sormann, Emanuele Santellani, Mattia Rossi +2
We propose a novel approach for deep learning-based Multi-View Stereo (MVS). For each pixel in the reference image, our method leverages a deep architecture to search for the corre…
FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion
Dominik Hirner, Friedrich Fraundorfer
We propose an accurate and lightweight convolutional neural network for stereo estimation with depth completion. We name this method fully-convolutional deformable similarity netwo…
MD-Net: Multi-Detector for Local Feature Extraction
Emanuele Santellani, Christian Sormann, Mattia Rossi +2
Establishing a sparse set of keypoint correspon dences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensi…
MCTS with Refinement for Proposals Selection Games in Scene Understanding
Sinisa Stekovic, Mahdi Rad, Alireza Moradi +2
We propose a novel method applicable in many scene understanding problems that adapts the Monte Carlo Tree Search (MCTS) algorithm, originally designed to learn to play games of hi…
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions
Christian Sormann, Mattia Rossi, Andreas Kuhn +1
We present a novel deep-learning-based method for Multi-View Stereo. Our method estimates high resolution and highly precise depth maps iteratively, by traversing the continuous sp…
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks
Stefan Ainetter, Christoph Böhm, Rohit Dhakate +2
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…
PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
Stefano Zorzi, Shabab Bazrafkan, Stefan Habenschuss +1
While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of e…
End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB
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 seman…
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer +1
We propose a novel method for reconstructing floor plans from noisy 3D point clouds. Our main contribution is a principled approach that relies on the Monte Carlo Tree Search (MCTS…
Monte Carlo Scene Search for 3D Scene Understanding
Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar +3
We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree S…
BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo
Christian Sormann, Patrick Knöbelreiter, Andreas Kuhn +3
In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a differentiable Conditional Random Field (CRF) layer for re…
FC-DCNN: A densely connected neural network for stereo estimation
Dominik Hirner, Friedrich Fraundorfer
We propose a novel lightweight network for stereo estimation. Our network consists of a fully-convolutional densely connected neural network (FC-DCNN) that computes matching costs…
Map-Repair: Deep Cadastre Maps Alignment and Temporal Inconsistencies Fix in Satellite Images
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. Moreover, due…
Regularization of Building Boundaries in Satellite Images using Adversarial and Regularized Losses
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 a…
Machine-learned Regularization and Polygonization of Building Segmentation Masks
Stefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer
We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. Taking an image as input, we first predict building seg…
Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences
Banglei Guan, Ji Zhao, Daniel Barath +1
We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting the relationshi…
Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
Patrick Knöbelreiter, Christian Sormann, Alexander Shekhovtsov +2
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models. The main diffi…
General 3D Room Layout from a Single View by Render-and-Compare
Sinisa Stekovic, Shreyas Hampali, Mahdi Rad +3
We present a novel method to reconstruct the 3D layout of a room (walls, floors, ceilings) from a single perspective view in challenging conditions, by contrast with previous singl…
Minimal Solutions for Relative Pose with a Single Affine Correspondence
Banglei Guan, Ji Zhao, Zhang Li +2
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 eff…
DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction
Andreas Kuhn, Christian Sormann, Mattia Rossi +2
Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and…