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

03/08/2023
by   Arthur Moreau, et al.
0

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.

READ FULL TEXT

page 1

page 4

page 6

page 8

research
04/06/2023

DeLiRa: Self-Supervised Depth, Light, and Radiance Fields

Differentiable volumetric rendering is a powerful paradigm for 3D recons...
research
05/31/2023

FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow

Reconstruction of 3D neural fields from posed images has emerged as a pr...
research
03/03/2023

Multi-Plane Neural Radiance Fields for Novel View Synthesis

Novel view synthesis is a long-standing problem that revolves around ren...
research
04/05/2022

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

We present iSDF, a continual learning system for real-time signed distan...
research
05/13/2020

Self-Supervised Deep Visual Odometry with Online Adaptation

Self-supervised VO methods have shown great success in jointly estimatin...
research
07/19/2021

GenRadar: Self-supervised Probabilistic Camera Synthesis based on Radar Frequencies

Autonomous systems require a continuous and dependable environment perce...
research
03/20/2023

Neural Implicit Vision-Language Feature Fields

Recently, groundbreaking results have been presented on open-vocabulary ...

Please sign up or login with your details

Forgot password? Click here to reset