CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation

Autor:	Moreau, Arthur, Piasco, Nathan, Bennehar, Moussab, Tsishkou, Dzmitry, Stanciulescu, Bogdan, de La Fortelle, Arnaud
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Beyond novel view synthesis, Neural Radiance Fields are useful for applications that interact with the real world. In this paper, we use them as an implicit map of a given scene and propose a camera relocalization algorithm tailored for this representation. The proposed method enables to compute in real-time the precise position of a device using a single RGB camera, during its navigation. In contrast with previous work, we do not rely on pose regression or photometric alignment but rather use dense local features obtained through volumetric rendering which are specialized on the scene with a self-supervised objective. As a result, our algorithm is more accurate than competitors, able to operate in dynamic outdoor environments with changing lightning conditions and can be readily integrated in any volumetric neural renderer. Comment: Accepted to ICCV 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.04869 Zobrazit plný text záznamu View this record from Arxiv