NOCaL: Calibration-Free Semi-Supervised Learning of Odometry and Camera Intrinsics
This work addresses the barrier of bespoke models and calibration for adopting emerging imaging technologies in robotics, representing a key step toward automating interpretation of general camera geometries.
The paper tackles the problem of interpreting previously unseen cameras without calibration by introducing NOCaL, a semi-supervised learning architecture that estimates camera parameters, relative pose, and scene appearance, demonstrating calibration-free odometry and novel view synthesis on rendered and captured imagery.
There are a multitude of emerging imaging technologies that could benefit robotics. However the need for bespoke models, calibration and low-level processing represents a key barrier to their adoption. In this work we present NOCaL, Neural odometry and Calibration using Light fields, a semi-supervised learning architecture capable of interpreting previously unseen cameras without calibration. NOCaL learns to estimate camera parameters, relative pose, and scene appearance. It employs a scene-rendering hypernetwork pretrained on a large number of existing cameras and scenes, and adapts to previously unseen cameras using a small supervised training set to enforce metric scale. We demonstrate NOCaL on rendered and captured imagery using conventional cameras, demonstrating calibration-free odometry and novel view synthesis. This work represents a key step toward automating the interpretation of general camera geometries and emerging imaging technologies.