Monocular Depth Estimation for Tilted Images via Gravity Rectifier - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Monocular Depth Estimation for Tilted Images via Gravity Rectifier

Résumé

Monocular depth estimation is a challenging task in computer vision. Although many approaches using Convolutional neural networks (CNNs) have been proposed, most of them are trained on large-scale datasets mainly composed of gravity-aligned images. Therefore, conventional approaches fail to predict reliable depth for tilted images containing large pitch and roll camera rotations. To tackle this problem, we propose a novel refining method based on the distribution of gravity directions in the training sets. We designed a gravity rectifier that is learned to transform the gravity direction of a tilted image into a rectified one that matches the gravity-aligned training data distribution. For the evaluation, we employed public datasets and also created our own dataset composed of large pitch and roll camera movements. Our experiments showed that our approach successfully rectified the camera rotation and outperformed our baselines, which achieved 29% improvement in abs rel over the vanilla model. Additionally, our method had competitive accuracy comparable to state-ofthe-art monocular depth prediction approaches considering camera rotation.
Fichier principal
Vignette du fichier
VISSAP_2023_YukiSaito_CameraReady.pdf (3.14 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04064627 , version 1 (11-04-2023)

Identifiants

Citer

Yuki Saito, Hideo Saito, Vincent Frémont. Monocular Depth Estimation for Tilted Images via Gravity Rectifier. 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023), Feb 2023, Lisbonne, Portugal. pp.453-463, ⟨10.5220/0011624600003417⟩. ⟨hal-04064627⟩
44 Consultations
90 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More