Instant Neural Radiance Fields
Thomas Müller, Alex Evans, Christoph Schied, M. Foco, András Bódis-Szomorú, Isaac Deutsch, Michael Shelley, Alexander Keller
Abstract
We extend our instant NeRF implementation [Müller et al. 2022] to allow training from an incremental stream of images and camera poses, provided by a realtime Simultaneous Localization And Mapping (SLAM) system. Camera poses are refined end-to-end by back-propagating the gradients from NeRF training. Reconstruction quality is further improved by compensating for various camera properties, such as rolling shutter, non-linear lens distortion, and variable exposure typical of digital cameras.
Topics & Concepts
InstantComputer scienceComputer visionArtificial intelligenceRadianceDistortion (music)Digital cameraLens (geology)ShutterComputer graphics (images)Remote sensingOpticsGeologyPhysicsComputer networkAmplifierQuantum mechanicsBandwidth (computing)Optical measurement and interference techniquesAdvanced Vision and ImagingRobotics and Sensor-Based Localization