Pregled bibliografske jedinice broj: 1093093
Towards Keypoint Guided Self-Supervised Depth Estimation
Towards Keypoint Guided Self-Supervised Depth Estimation // Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4) / Farinella, Giovanni Maria ; Radeva, Petia ; Braz, Jose (ur.).
Valletta, Malta: SCITEPRESS, 2020. str. 583-589 doi:10.5220/0009190005830589 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1093093 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Towards Keypoint Guided Self-Supervised Depth
Estimation
Autori
Bartol, Kristijan ; Bojanić, David ; Petković, Tomislav ; Pribanić, Tomislav ; Donoso, Yago
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4)
/ Farinella, Giovanni Maria ; Radeva, Petia ; Braz, Jose - : SCITEPRESS, 2020, 583-589
ISBN
978-989-758-402-2
Skup
15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020)
Mjesto i datum
Valletta, Malta, 27.02.2020. - 29.02.2020
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Monocular Depth Estimation ; Self-supervised Learning ; Keypoint Similarity Loss
Sažetak
This paper proposes to use keypoints as a self- supervision clue for learning depth map estimation from a collection of input images. As ground truth depth from real images is difficult to obtain, there are many unsupervised and self- supervised approaches to depth estimation that have been proposed. Most of these unsupervised approaches use depth map and ego-motion estimations to reproject the pixels from the current image into the adjacent image from the image collection. Depth and ego-motion estimations are evaluated based on pixel intensity differences between the correspondent original and reprojected pixels. Instead of reprojecting the individual pixels, we propose to first select image keypoints in both images and then reproject and compare the correspondent keypoints of the two images. The keypoints should describe the distinctive image features well. By learning a deep model with and without the keypoint extraction technique, we show that using the keypoints improve the depth e stimation learning. We also propose some future directions for keypoint-guided learning of structure-from- motion problems.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
HRZZ-IP-2018-01-8118 - Izračun antropometrijskih mjera pametnim telefonom i tabletom (STEAM) (Pribanić, Tomislav, HRZZ ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Profili:
Tomislav Petković (autor)
Kristijan Bartol (autor)
Tomislav Pribanić (autor)
David Bojanić (autor)