Search Results for author:
Found 34 papers, 12 papers with code
Automatically Annotating Indoor Images with CAD Models via RGB-D Scans
We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans.
DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo
We denote our method DELS-MVS: Deep Epipolar Line Search Multi-View Stereo.
FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion
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.
MD-Net: Multi-Detector for Local Feature Extraction
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.
MCTS with Refinement for Proposals Selection Games in Scene Understanding
We also introduce a novel differentiable method for rendering the polygonal shapes of these proposals.
PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
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.
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions
We present a novel deep-learning-based method for Multi-View Stereo.
Ranked #6 on
3D Reconstruction
on DTU
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks
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.
End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB
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.
Ranked #1 on
Robotic Grasping
on Cornell Grasp Dataset
MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals.
Monte Carlo Scene Search for 3D Scene Understanding
We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data.
BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo
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
The output of this network is used in order to calculate matching costs and create a cost-volume.
Machine-learned Regularization and Polygonization of Building Segmentation Masks
We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks.
Map-Repair: Deep Cadastre Maps Alignment and Temporal Inconsistencies Fix in Satellite Images
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.
Regularization of Building Boundaries in Satellite Images using Adversarial and Regularized Losses
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.
Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences
We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs).
Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems
It has been proposed by many researchers that combining deep neural networks with graphical models can create more efficient and better regularized composite models.
General 3D Room Layout from a Single View by Render-and-Compare
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
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.
DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction
Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions.
Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning
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.
S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation
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.
Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization
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.
Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
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.
Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems
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.
Evaluation of CNN-based Single-Image Depth Estimation Methods
While an increasing interest in deep models for single-image depth estimation methods can be observed, established schemes for their evaluation are still limited.
Prioritized Multi-View Stereo Depth Map Generation Using Confidence Prediction
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.
Deep learning in remote sensing: a review
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.
3D Visual Perception for Self-Driving Cars using a Multi-Camera System: Calibration, Mapping, Localization, and Obstacle Detection
To minimize the number of cameras needed for surround perception, we utilize fisheye cameras.
Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity
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).
UAV-based Autonomous Image Acquisition with Multi-View Stereo Quality Assurance by Confidence Prediction
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.
Using Self-Contradiction to Learn Confidence Measures in Stereo Vision
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
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.
