Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization

Abstract

Most image colorization systems operate in Lab space by predicting chroma (ab) while preserving an input-derived luminance channel (L). While effective on standard benchmarks, this fixed-luminance design restricts brightness changes and becomes unreliable when grayscale formation deviates from natural-image luminance, as in historical orthochromatic photography. We propose a luminance-agnostic colorization framework that formulates colorization as full-RGB image editing using a foundation image-editing model. To bridge modern panchromatic and historical orthochromatic conditions, we introduce a mixed grayscale objective that trains the model under both standard luminance grayscale and a red-insensitive grayscale formation. Experiments on COCO, ImageNet, and a multi-instance benchmark show that our method is competitive on standard grayscale inputs and substantially more robust under orthochromatic inputs, with qualitative comparisons and a human study indicating fewer visible color artifacts.

BibTeX

@inproceedings{maheshwari2026beyond,
  title     = {Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization},
  author    = {Maheshwari, Swarnim and Ali, Syed Imam and Balasubramanian, Vineeth N.},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}

@article{maheshwari2026beyondarxiv,
  title   = {Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization},
  author  = {Maheshwari, Swarnim and Ali, Syed Imam and Balasubramanian, Vineeth N.},
  journal = {arXiv preprint arXiv:2608.10798},
  year    = {2026}
}