Multispectral Illumination Estimation using Deep Unrolling Network

Yuqi Li, Qiang Fu, Wolfgang Heidrich,
ICCV, 2021

Figure 1: The framework of our spectral reflectance and illumination estimation method(left). Estimated illumination spectra and reflectance images of a real scene - "book"(right).


This paper examines the problem of illumination spectra estimation in multispectral images. We cast the problem into a constrained matrix factorization problem and present a method for both single-global and multiple illumination estimation in which a deep unrolling network is constructed from the ADMM optimization for solving the matrix factorization problem. To alleviate the lack of multispectral training data, we build a large multispectral reflectance image dataset for generating synthesized data and use them for training and evaluating our model. The results of simulations and real experiments demonstrate that the proposed method is able to outperform state-of-the-art spectral illumination estimation methods, and that it generalizes well to a wide variety of scenes and spectra.

Figure 2: Our spectral reflectance image dataset.

Figure 3: Global illumination estimation.


Paper_fullres: [Coming soon] 
Code: [Coming soon] 


  title={Multispectral illumination estimation using deep unrolling network},
  author={Li, Yuqi and Fu, Qiang and Heidrich, Wolfgang},
  booktitle={2021 IEEE International Conference on Computer Vision(ICCV)},