BrightFlow: Brightness-Change-Aware Unsupervised Learning of Optical Flow - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

BrightFlow: Brightness-Change-Aware Unsupervised Learning of Optical Flow

Florian Chabot
  • Fonction : Auteur
Angelique Loesch
  • Fonction : Auteur
Hichem Sahbi

Résumé

Unsupervised optical flow estimation relies on the assumption that pixels characterizing the same observed object should exhibit a stable appearance across video frames. With this assumption, the long-standing principle behind flow estimation consists in optimizing a photometric loss that maximizes the similarity between paired pixels in successive frames. However, these frames could be subject to strong brightness changes due to the radiometric properties of scenes as well as their viewing conditions. In this paper, we present BrightFlow, a new method to train any optical flow estimation network in an unsupervised manner. It consists in training two networks that jointly estimate optical flow and brightness changes. These changes are then compensated in the photometric loss so that reconstruction errors due to shadows or reflections will not affect negatively the training. As this compensation mechanism is only used at training stage, our method does not impact the number of parameters or the complexity at inference. Extensive experiments conducted on standard datasets and optical flow architectures show a consistent gain of our method. Source code is available at https://github.com/CEA-LIST/BrightFlow.
Fichier principal
Vignette du fichier
Marsal_BrightFlow_Brightness-Change-Aware_Unsupervised_Learning_of_Optical_Flow_WACV_2023_paper.pdf (1.61 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04042615 , version 1 (23-03-2023)

Identifiants

Citer

Rémi Marsal, Florian Chabot, Angelique Loesch, Hichem Sahbi. BrightFlow: Brightness-Change-Aware Unsupervised Learning of Optical Flow. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2023, Waikoloa, United States. pp.2060-2069, ⟨10.1109/WACV56688.2023.00210⟩. ⟨hal-04042615⟩
34 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More