Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees. / Oancea, Cosmin Eugen; Robroek, Ties ; Gieseke, Fabian Cristian.

Proceedings of the IEEE International Conference on Big Data (BigData2020). 10. udg. IEEE, 2020. s. 5172-5181.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Oancea, CE, Robroek, T & Gieseke, FC 2020, Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees. i Proceedings of the IEEE International Conference on Big Data (BigData2020). 10 udg, IEEE, s. 5172-5181, 2020 IEEE International Conference on Big Data (BigData2020), Virtual, 10/12/2020. https://doi.org/10.1109/BigData50022.2020.9378426

APA

Oancea, C. E., Robroek, T., & Gieseke, F. C. (2020). Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees. I Proceedings of the IEEE International Conference on Big Data (BigData2020) (10 udg., s. 5172-5181). IEEE. https://doi.org/10.1109/BigData50022.2020.9378426

Vancouver

Oancea CE, Robroek T, Gieseke FC. Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees. I Proceedings of the IEEE International Conference on Big Data (BigData2020). 10 udg. IEEE. 2020. s. 5172-5181 https://doi.org/10.1109/BigData50022.2020.9378426

Author

Oancea, Cosmin Eugen ; Robroek, Ties ; Gieseke, Fabian Cristian. / Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees. Proceedings of the IEEE International Conference on Big Data (BigData2020). 10. udg. IEEE, 2020. s. 5172-5181

Bibtex

@inproceedings{33771ba30bad4cf8a6edd94b63b32d74,
title = "Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees",
abstract = "Nearest neighbour fields accurately and intuitively describe the transformation between two images and have been heavily used in computer vision. Generating such fields, however, is not an easy task due to the induced computational complexity, which quickly grows with the sizes of the images. Modern parallel devices such as graphics processing units depict a viable way of reducing the practical run time of such compute-intensive tasks. In this work, we propose a novel parallel implementation for one of the state-of-the-art methods for the computation of nearest neighbour fields, called p ropagation-assisted k -d trees. The resulting implementation yields valuable computational savings over a corresponding multi-core implementation. Additionally, it is tuned to consume only little additional memory and is, hence, capable of dealing with high-resolution image data, which is vital as image quality standards keep rising",
author = "Oancea, {Cosmin Eugen} and Ties Robroek and Gieseke, {Fabian Cristian}",
year = "2020",
doi = "10.1109/BigData50022.2020.9378426",
language = "English",
pages = "5172--5181",
booktitle = "Proceedings of the IEEE International Conference on Big Data (BigData2020)",
publisher = "IEEE",
edition = "10",
note = "2020 IEEE International Conference on Big Data (BigData2020) ; Conference date: 10-12-2020 Through 13-12-2020",

}

RIS

TY - GEN

T1 - Approximate Nearest-Neighbour Fields via Massively-Parallel Propagation-Assisted K-D Trees

AU - Oancea, Cosmin Eugen

AU - Robroek, Ties

AU - Gieseke, Fabian Cristian

PY - 2020

Y1 - 2020

N2 - Nearest neighbour fields accurately and intuitively describe the transformation between two images and have been heavily used in computer vision. Generating such fields, however, is not an easy task due to the induced computational complexity, which quickly grows with the sizes of the images. Modern parallel devices such as graphics processing units depict a viable way of reducing the practical run time of such compute-intensive tasks. In this work, we propose a novel parallel implementation for one of the state-of-the-art methods for the computation of nearest neighbour fields, called p ropagation-assisted k -d trees. The resulting implementation yields valuable computational savings over a corresponding multi-core implementation. Additionally, it is tuned to consume only little additional memory and is, hence, capable of dealing with high-resolution image data, which is vital as image quality standards keep rising

AB - Nearest neighbour fields accurately and intuitively describe the transformation between two images and have been heavily used in computer vision. Generating such fields, however, is not an easy task due to the induced computational complexity, which quickly grows with the sizes of the images. Modern parallel devices such as graphics processing units depict a viable way of reducing the practical run time of such compute-intensive tasks. In this work, we propose a novel parallel implementation for one of the state-of-the-art methods for the computation of nearest neighbour fields, called p ropagation-assisted k -d trees. The resulting implementation yields valuable computational savings over a corresponding multi-core implementation. Additionally, it is tuned to consume only little additional memory and is, hence, capable of dealing with high-resolution image data, which is vital as image quality standards keep rising

U2 - 10.1109/BigData50022.2020.9378426

DO - 10.1109/BigData50022.2020.9378426

M3 - Article in proceedings

SP - 5172

EP - 5181

BT - Proceedings of the IEEE International Conference on Big Data (BigData2020)

PB - IEEE

T2 - 2020 IEEE International Conference on Big Data (BigData2020)

Y2 - 10 December 2020 through 13 December 2020

ER -

ID: 258658900