English

Array Camera Image Fusion using Physics-Aware Transformers

Computer Vision and Pattern Recognition 2022-07-07 v1 Image and Video Processing

Abstract

We demonstrate a physics-aware transformer for feature-based data fusion from cameras with diverse resolution, color spaces, focal planes, focal lengths, and exposure. We also demonstrate a scalable solution for synthetic training data generation for the transformer using open-source computer graphics software. We demonstrate image synthesis on arrays with diverse spectral responses, instantaneous field of view and frame rate.

Keywords

Cite

@article{arxiv.2207.02250,
  title  = {Array Camera Image Fusion using Physics-Aware Transformers},
  author = {Qian Huang and Minghao Hu and David Jones Brady},
  journal= {arXiv preprint arXiv:2207.02250},
  year   = {2022}
}
R2 v1 2026-06-24T12:14:57.436Z