MBA-VO : Motion blur aware visual odometry
(2021) 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 p.5530-5539- Abstract
- Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a novel hybrid visual odometry pipeline with direct approach that explicitly models and estimates the camera’s local trajectory within the exposure time. This allows us to actively compensate for any motion blur that occurs due to the camera motion. In addition, we also contribute a novel benchmarking dataset for motion blur aware visual odometry. In experiments we show that by directly modeling the image formation process, we are able to improve robustness of the visual odometry, while keeping comparable... (More)
- Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a novel hybrid visual odometry pipeline with direct approach that explicitly models and estimates the camera’s local trajectory within the exposure time. This allows us to actively compensate for any motion blur that occurs due to the camera motion. In addition, we also contribute a novel benchmarking dataset for motion blur aware visual odometry. In experiments we show that by directly modeling the image formation process, we are able to improve robustness of the visual odometry, while keeping comparable accuracy as that for images without motion blur. Both the code and the datasets can be found from https://github.com/ethliup/MBA-VO. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/e53755ec-f3ec-48d9-ac10-2fbc6fcd7b0e
- author
- Liu, Peidong ; Zuo, Xingxing ; Larsson, Viktor LU and Pollefeys, Marc
- publishing date
- 2021
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- pages
- 10 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021
- conference location
- Virtual, Online, Canada
- conference dates
- 2021-10-11 - 2021-10-17
- external identifiers
-
- scopus:85127437786
- DOI
- 10.1109/ICCV48922.2021.00550
- language
- English
- LU publication?
- no
- id
- e53755ec-f3ec-48d9-ac10-2fbc6fcd7b0e
- date added to LUP
- 2022-09-06 13:19:29
- date last changed
- 2022-09-20 18:52:22
@inproceedings{e53755ec-f3ec-48d9-ac10-2fbc6fcd7b0e, abstract = {{Motion blur is one of the major challenges remaining for visual odometry methods. In low-light conditions where longer exposure times are necessary, motion blur can appear even for relatively slow camera motions. In this paper we present a novel hybrid visual odometry pipeline with direct approach that explicitly models and estimates the camera’s local trajectory within the exposure time. This allows us to actively compensate for any motion blur that occurs due to the camera motion. In addition, we also contribute a novel benchmarking dataset for motion blur aware visual odometry. In experiments we show that by directly modeling the image formation process, we are able to improve robustness of the visual odometry, while keeping comparable accuracy as that for images without motion blur. Both the code and the datasets can be found from https://github.com/ethliup/MBA-VO.}}, author = {{Liu, Peidong and Zuo, Xingxing and Larsson, Viktor and Pollefeys, Marc}}, booktitle = {{2021 IEEE/CVF International Conference on Computer Vision (ICCV)}}, language = {{eng}}, pages = {{5530--5539}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{MBA-VO : Motion blur aware visual odometry}}, url = {{http://dx.doi.org/10.1109/ICCV48922.2021.00550}}, doi = {{10.1109/ICCV48922.2021.00550}}, year = {{2021}}, }