Cascading Convolutional Color Constancy


  • Huanglin Yu South China University of Technology
  • Ke Chen South China University of Technology
  • Kaiqi Wang South China University of Technology
  • Yanlin Qian Tampere University
  • Zhaoxiang Zhang Chinese Academy of Sciences
  • Kui Jia South China University of Technology



Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy. However, it's still challenging due to intrinsic appearance and label ambiguities caused by unknown illuminants, diverse reflection properties of materials and extrinsic imaging factors (such as different camera sensors). In this paper, we introduce a novel algorithm – Cascading Convolutional Color Constancy (in short, C4) to improve robustness of regression learning and achieve stable generalization capability across datasets (different cameras and scenes) in a unique framework. The proposed C4 method ensembles a series of dependent illumination hypotheses from each cascade stage via introducing a weighted multiply-accumulate loss function, which can inherently capture different modes of illuminations and explicitly enforce coarse-to-fine network optimization. Experimental results on the public Color Checker and NUS 8-Camera benchmarks demonstrate superior performance of the proposed algorithm in comparison with the state-of-the-art methods, especially for more difficult scenes.




How to Cite

Yu, H., Chen, K., Wang, K., Qian, Y., Zhang, Z., & Jia, K. (2020). Cascading Convolutional Color Constancy. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12725-12732.



AAAI Technical Track: Vision