Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application

Autor:	Qiu, Xuchong, Xiao, Yang, Wang, Chaohui, Marlet, Renaud
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images. Experiments on a variety of datasets demonstrate that our method outperforms existing ones on this task. To further illustrate the value of our formulation, we also propose a new depth map refinement method that consistently improve the performance of state-of-the-art monocular depth estimation methods. Our code and data are available at http://imagine.enpc.fr/~qiux/P2ORM/. Comment: Accepted to ECCV 2020 as a spotlight. Project page: http://imagine.enpc.fr/~qiux/P2ORM/
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2007.12088 Zobrazit plný text záznamu View this record from Arxiv