TY - GEN
T1 - Pixel-Wise Color Constancy Via Smoothness Techniques In Multi-Illuminant Scenes
AU - Entok, Umut Cem
AU - Laakom, Firas
AU - Pakdaman, Farhad
AU - Gabbouj, Moncef
PY - 2024
Y1 - 2024
N2 - Most scenes are illuminated by several light sources, where the traditional assumption of uniform illumination is invalid. This issue is ignored in most color constancy methods, primarily due to the complex spatial impact of multiple light sources on the image. Moreover, most existing multi-illuminant methods fail to preserve the smooth change of illumination, which stems from spatial dependencies in natural images. Motivated by this, we propose a novel multi-illuminant color constancy method, by learning pixel-wise illumination maps caused by multiple light sources. The proposed method enforces smoothness within neighboring pixels, by regularizing the training with the total variation loss. Moreover, a bilateral filter is provisioned further to enhance the natural appearance of the estimated images, while preserving the edges. Additionally, we propose a label-smoothing technique that enables the model to generalize well despite the uncertainties in ground truth. Quantitative and qualitative experiments demonstrate that the proposed method outperforms the state-of-the-art.
AB - Most scenes are illuminated by several light sources, where the traditional assumption of uniform illumination is invalid. This issue is ignored in most color constancy methods, primarily due to the complex spatial impact of multiple light sources on the image. Moreover, most existing multi-illuminant methods fail to preserve the smooth change of illumination, which stems from spatial dependencies in natural images. Motivated by this, we propose a novel multi-illuminant color constancy method, by learning pixel-wise illumination maps caused by multiple light sources. The proposed method enforces smoothness within neighboring pixels, by regularizing the training with the total variation loss. Moreover, a bilateral filter is provisioned further to enhance the natural appearance of the estimated images, while preserving the edges. Additionally, we propose a label-smoothing technique that enables the model to generalize well despite the uncertainties in ground truth. Quantitative and qualitative experiments demonstrate that the proposed method outperforms the state-of-the-art.
U2 - 10.1109/ICIP51287.2024.10647547
DO - 10.1109/ICIP51287.2024.10647547
M3 - Conference contribution
T3 - Proceedings : International Conference on Image Processing
SP - 2737
EP - 2743
BT - 2024 IEEE International Conference on Image Processing (ICIP)
PB - IEEE
T2 - IEEE International Conference on Image Processing
Y2 - 27 October 2024 through 30 October 2024
ER -