Book ChapterDOI
Multimodal Dense Stereo Matching
Max Mehltretter,Sebastian P. Kleinschmidt,Bernardo Wagner,Christian Heipke +3 more
- pp 407-421
Reads0
Chats0
TLDR
This paper proposes a new approach for dense depth estimation based on multimodal stereo images that employs a combined cost function utilizing robust metrics and a transformation to an illumination independent representation and presents a confidence based weighting scheme which allows a pixel-wise weight adjustment within the cost function.Abstract:
In this paper, we propose a new approach for dense depth estimation based on multimodal stereo images. Our approach employs a combined cost function utilizing robust metrics and a transformation to an illumination independent representation. Additionally, we present a confidence based weighting scheme which allows a pixel-wise weight adjustment within the cost function. We demonstrate the capabilities of our approach using RGB- and thermal images. The resulting depth maps are evaluated by comparing them to depth measurements of a Velodyne HDL-64E LiDAR sensor. We show that our method outperforms current state of the art dense matching methods regarding depth estimation based on multimodal input images.read more
Citations
More filters
Journal Article
HeatWave : a handheld 3D thermography system for energy auditing
Stephen Vidas,Peyman Moghadam +1 more
TL;DR: In this paper, a handheld 3D thermography system consisting of two commercially available imaging sensors and a set of software algorithms can be run on a laptop to generate detailed 3D surface temperature models for energy auditing.
Journal ArticleDOI
Aleatoric uncertainty estimation for dense stereo matching via CNN-based cost volume analysis
Max Mehltretter,Christian Heipke +1 more
TL;DR: A new Convolutional Neural Network architecture is presented to directly learn features for the task of aleatoric uncertainty estimation from volumetric 3D data and the generality and state-of-the-art accuracy of the proposed method are demonstrated.
Proceedings ArticleDOI
Robust Calibration Procedure of a Manipulator and a 2D Laser Scanner using a 1D Calibration Target.
TL;DR: This paper presents a simple but effective approach to determine the six degrees of freedom transformation between the end effector of a serial manipulator and the center of a 2D laser scanner using only a 1D target for calibration.
Posted Content
CNN-based Cost Volume Analysis as Confidence Measure for Dense Matching
Max Mehltretter,Christian Heipke +1 more
TL;DR: This paper proposes a novel Convolutional Neural Network architecture to directly learn features for confidence estimation from volumetric 3D data, and demonstrates the generality and state-of-the-art accuracy of the proposed method.
Proceedings ArticleDOI
Cross-Spectral Neural Radiance Fields
Matteo Poggi,Pierluigi Zama Ramirez,Fabio Tosi,Samuele Salti,Stefano Mattoccia,Luigi Di Stefano +5 more
TL;DR: X-NeRF optimizes camera poses across spectra during training and exploits Normalized Cross-Device Coordinates to render images of different modalities from arbitrary viewpoints, which are aligned and at the same resolution.
References
More filters
Journal ArticleDOI
Stereo Processing by Semiglobal Matching and Mutual Information
TL;DR: This paper describes the Semi-Global Matching (SGM) stereo method, which uses a pixelwise, Mutual Information based matching cost for compensating radiometric differences of input images and demonstrates a tolerance against a wide range of radiometric transformations.
Book ChapterDOI
Non-parametric local transforms for computing visual correspondence
Ramin Zabih,John Iselin Woodfill +1 more
TL;DR: A new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation, which can result in improved performance near object boundaries when compared with conventional methods such as normalized correlation.
Image Features From Phase Congruency
TL;DR: Videre: Journal of Computer Vision Research is a quarterly journal published electronically on the Internet by The MIT Press, Cambridge, Massachusetts, 02142 and prices subject to change without notice.
Journal Article
Stereo matching by training a convolutional neural network to compare image patches
Jure Žbontar,Yann LeCun +1 more
TL;DR: In this paper, the first stage of many stereo algorithms, matching cost computation, is addressed by learning a similarity measure on small image patches using a convolutional neural network, and then a series of post-processing steps follow: cross-based cost aggregation, semiglobal matching, left-right consistency check, subpixel enhancement, a median filter, and a bilateral filter.
Book ChapterDOI
Efficient large-scale stereo matching
TL;DR: A novel approach to binocular stereo for fast matching of high-resolution images by building a prior on the disparities by forming a triangulation on a set of support points which can be robustly matched, reducing the matching ambiguities of the remaining points.