Towards Keypoint Guided Self-Supervised Depth Estimation (CROSBI ID 696661)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Bartol, Kristijan ; Bojanić, David ; Petković, Tomislav ; Pribanić, Tomislav ; Donoso, Yago
engleski
Towards Keypoint Guided Self-Supervised Depth Estimation
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.
Monocular Depth Estimation ; Self-supervised Learning ; Keypoint Similarity Loss
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
583-589.
2020.
objavljeno
10.5220/0009190005830589
Podaci o matičnoj publikaciji
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
978-989-758-402-2
Podaci o skupu
15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020)
predavanje
27.02.2020-29.02.2020
Valletta, Malta