Fast Nonlinear Image Unblending
Fast Nonlinear Image Unblending
复制标题
DOI：
10.1109/wacv51458.2022.00325
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Daichi Horita;K. Aizawa;Ryohei Suzuki;Taizan Yonetsuji;Huachun Zhu
中科院分区：
文献类型：
--
作者：
Daichi Horita;K. Aizawa;Ryohei Suzuki;Taizan Yonetsuji;Huachun Zhu
非线性颜色混合是一种以“叠加”和“乘法”等混合模式表示的高级混合，被数字创作者广泛采用，以产生有吸引力的视觉效果。然而，为了在现有位图图像（如照片）上享受如此灵活的编辑方式，创作者需要一种快速的非线性混合算法，将图像分解为一组半透明图层。为了解决这个问题，我们提出了一种基于神经网络的方法，用于将输入图像非线性分解为线性和非线性 Alpha 层，这些层可以根据指定的调色板和混合模式单独修改以用于编辑目的。实验表明，我们提出的方法的推理速度比最先进的非线性图像解混合方法快 370 倍，后者使用计算密集型迭代优化。此外，我们的重建质量比其他方法（包括线性混合模型）更高或相当。此外，我们还提供了将我们的方法应用于具有非线性混合模式的图像编辑的示例。
Nonlinear color blending, which is advanced blending indicated by blend modes such as "overlay" and "multiply," is extensively employed by digital creators to produce attractive visual effects. To enjoy such flexible editing modalities on existing bitmap images like photographs, however, creators need a fast nonlinear blending algorithm that decomposes an image into a set of semi-transparent layers. To address this issue, we propose a neural-network-based method for nonlinear decomposition of an input image into linear and nonlinear alpha layers that can be separately modified for editing purposes, based on the specified color palettes and blend modes. Experiments show that our proposed method achieves an inference speed 370 times faster than the state-of-the-art method of nonlinear image unblending, which uses computationally intensive iterative optimization. Furthermore, our reconstruction quality is higher or comparable than other methods, including linear blending models. In addition, we provide examples that apply our method to image editing with nonlinear blend modes.