Search Results - "Hane, Christian"
-
1
Hierarchical Surface Prediction
Published in IEEE transactions on pattern analysis and machine intelligence (01-06-2020)“…Recently, Convolutional Neural Networks have shown promising results for 3D geometry prediction. They can make predictions from very little input data such as…”
Get full text
Journal Article -
2
Large-scale outdoor 3D reconstruction on a mobile device
Published in Computer vision and image understanding (01-04-2017)“…•Approach for reconstructing large-scale outdoor scenes using monocular motion stereo.•Runs at interactive frame rates on a Google Project Tango Development…”
Get full text
Journal Article -
3
Obstacle detection for self-driving cars using only monocular cameras and wheel odometry
Published in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (01-09-2015)“…Mapping the environment is crucial to enable path planning and obstacle avoidance for self-driving vehicles and other robots. In this paper, we concentrate on…”
Get full text
Conference Proceeding -
4
Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality
Published in IEEE transactions on image processing (01-01-2024)“…We study the visual quality judgments of human subjects on digital human avatars (sometimes referred to as "holograms" in the parlance of virtual reality [VR]…”
Get full text
Journal Article -
5
Multiresolution Deep Implicit Functions for 3D Shape Representation
Published in 2021 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2021)“…We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform…”
Get full text
Conference Proceeding -
6
Real-Time Direct Dense Matching on Fisheye Images Using Plane-Sweeping Stereo
Published in 2014 2nd International Conference on 3D Vision (01-12-2014)“…In this paper, we propose an adaptation of camera projection models for fisheye cameras into the plane-sweeping stereo matching algorithm. This adaptation…”
Get full text
Conference Proceeding -
7
Class Specific 3D Object Shape Priors Using Surface Normals
Published in 2014 IEEE Conference on Computer Vision and Pattern Recognition (01-06-2014)“…Dense 3D reconstruction of real world objects containing textureless, reflective and specular parts is a challenging task. Using general smoothness priors such…”
Get full text
Conference Proceeding -
8
Direction matters: Depth estimation with a surface normal classifier
Published in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2015)“…In this work we make use of recent advances in data driven classification to improve standard approaches for binocular stereo matching and single view depth…”
Get full text
Conference Proceeding -
9
Discrete optimization of ray potentials for semantic 3D reconstruction
Published in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2015)“…Dense semantic 3D reconstruction is typically formulated as a discrete or continuous problem over label assignments in a voxel grid, combining semantic and…”
Get full text
Conference Proceeding -
10
Segment based 3D object shape priors
Published in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2015)“…Dense 3D reconstruction still remains a hard task for a broad number of object classes which are not sufficiently textured or contain transparent and…”
Get full text
Conference Proceeding -
11
3D visual perception for self-driving cars using a multi-camera system: Calibration, mapping, localization, and obstacle detection
Published in Image and vision computing (01-12-2017)“…Cameras are a crucial exteroceptive sensor for self-driving cars as they are low-cost and small, provide appearance information about the environment, and work…”
Get full text
Journal Article -
12
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-01-2021)“…This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate…”
Get full text
Conference Proceeding -
13
Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning
Published in Proceedings of the National Academy of Sciences - PNAS (05-11-2019)“…Computed tomography (CT) of the head is used worldwide to diagnose neurologic emergencies. However, expertise is required to interpret these scans, and even…”
Get full text
Journal Article -
14
What Is Optimized in Convex Relaxations for Multilabel Problems: Connecting Discrete and Continuously Inspired MAP Inference
Published in IEEE transactions on pattern analysis and machine intelligence (01-01-2014)“…In this work, we present a unified view on Markov random fields (MRFs) and recently proposed continuous tight convex relaxations for multilabel assignment in…”
Get full text
Journal Article -
15
Dense Semantic 3D Reconstruction
Published in IEEE transactions on pattern analysis and machine intelligence (01-09-2017)“…Both image segmentation and dense 3D modeling from images represent an intrinsically ill-posed problem. Strong regularizers are therefore required to constrain…”
Get full text
Journal Article -
16
Deep Implicit Volume Compression
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2020)“…We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress…”
Get full text
Conference Proceeding -
17
Learning Independent Object Motion From Unlabelled Stereoscopic Videos
Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2019)“…We present a system for learning motion maps of independently moving objects from stereo videos. The only annotations used in our system are 2D object bounding…”
Get full text
Conference Proceeding -
18
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…We propose an approach for dense semantic 3D reconstruction which uses a data term that is defined as potentials over viewing rays, combined with continuous…”
Get full text
Conference Proceeding -
19
Joint 3D Scene Reconstruction and Class Segmentation
Published in 2013 IEEE Conference on Computer Vision and Pattern Recognition (01-06-2013)“…Both image segmentation and dense 3D modeling from images represent an intrinsically ill-posed problem. Strong regularizers are therefore required to constrain…”
Get full text
Conference Proceeding -
20
An overview of recent progress in volumetric semantic 3D reconstruction
Published in 2016 23rd International Conference on Pattern Recognition (ICPR) (01-12-2016)“…This paper gives an overview of a recently proposed method of solving dense 3D reconstruction and semantic segmentation from multiple input images in a joint…”
Get full text
Conference Proceeding