Buzzelli Marco, Bianco Simone
IEEE Trans Neural Netw Learn Syst. 2025 Jul;36(7):13387-13401. doi: 10.1109/TNNLS.2024.3454484.
We introduce a convolutional framework (CF) for computational color constancy, building upon the established low-level image feature-based framework, which utilized simple image statistics for illuminant estimation. Our framework expands upon this through an end-to-end learnable neural architecture. This adaptation enables the learning and usage of advanced filters that are not restricted to Gaussian kernels operating on individual color channels, thus generalizing the capabilities of the original framework. Additionally, our general framework supports deeper convolutional architectures, thus increasing its computational power. It can also be efficiently applied to estimate multiple spatially varying illuminants within a single scene. Our experimental results on standard datasets demonstrate that the CF outperforms the best methods in the low-level framework, improving the illuminant estimation accuracy by up to 34% for single illuminant estimation and 30% for multiple illuminants estimation. Additionally, our framework exhibits superior performance even when the number of training images is reduced. Finally, we document the inference speedup of our implementation reaching up to $30\times $ , making the CF especially suitable for applications where efficiency is critical. Source code and trained models available at: https://github.com/MarcoBauzz/convolutional-color-constancy.
我们基于已有的基于低级图像特征的框架，引入了一种用于计算颜色恒常性的卷积框架（CF），该框架利用简单的图像统计量进行光源估计。我们的框架通过端到端可学习的神经架构对此进行了扩展。这种调整使得能够学习和使用不限于在单个颜色通道上操作的高斯核的高级滤波器，从而扩展了原始框架的能力。此外，我们的通用框架支持更深的卷积架构，从而提高了其计算能力。它还可以有效地应用于估计单个场景内多个空间变化的光源。我们在标准数据集上的实验结果表明，CF在低级框架中优于最佳方法，对于单光源估计，光源估计精度提高了34%，对于多光源估计，提高了30%。此外，即使训练图像数量减少，我们的框架也表现出卓越的性能。最后，我们记录了我们实现的推理加速高达30倍，这使得CF特别适用于效率至关重要的应用。源代码和训练模型可在以下网址获取：https://github.com/MarcoBauzz/convolutional-color-constancy 。
