ID 原文 译文
40076 首先，加入调整优化能力更强的可形变卷积，以便于提取相邻帧图像的大位移和细节等空间特征； Firstly, the deformable convolution with stronger adjustment and optimization ability is added to extract the spatial features such as large displacement and details of adjacent frame images.
40077 然后利用基于注意力机制生成特征关联层，将相邻两帧的特征进行融合，以其作为由反卷积和上采样构成的解码部分的输入，旨在克服基于特征匹配等估计光流传统方法精度低的缺点； Then, the feature correlation layer is generated by using the attentionbased mechanism to carry out the feature fusion of the two adjacent frames, which is used as the input of the decoding part composed of deconvolution and upsampling and aims to overcome the disadvantage of low accuracy for the traditional methods of estimating optical flow based on feature matching.
40078 最后将得到的估计光流通过多网络堆栈的循环优化模型实现最终的光流估计。 And finally the above estimated optical flow is optimized with a set of network stack.
40079 实验表明，本文网络模型在处理遮挡、大位移和细节呈现等方面的表现优于现有方法。 Experiments show that the proposed network model performs better than existing methods in dealing with occlusion, large displacement and detail presentation.
40080 常规的非均匀照明图像增强方法在增强低光照区域细节时，容易对图像过度增强而导致结果失真。 Some existing enhancement methods enhance uneven lighting images by bringing out the details in the dark areas, but easily result in over-enhancement.
40081 本文从一种新的角度提出了Retinex模型的一种扩展形式，并用于非均匀照明图像的增强。 In this paper, an extended form of Retinex is proposed from a new viewpoint and applied to uneven lighting image enhancement.
40082 该算法将中心环绕Retinex模型输出作为感知反射率，将图像分解为感知光照图像和感知反射率图像，通过调整感知光照图像，再重新组合感知光照和感知反射率图像，得到增强结果。 Taking the centersurround Retinex output as the perceived reflectance, the proposed algorithm decomposes an image into a perceived reflectance image and a perceived illumination one.Image enhancement can be achieved by adjusting the perceived illumination image and combining back both images.
40083 与近几年来多种图像增强算法的主客观评估对比实验结果表明，该算法对非均匀光照图像具有良好的增强效果，能够有效增强图像亮度和细节，提高图像质量。 Experimental comparisons with some state-of the-art methods show that the proposed method has good performance on enhancing brightness and details, and improving the image quality for uneven lighting images.
40084 针对数据挖掘模型中存在的隐私泄漏问题及现有隐私保护技术的不透明性，本文将差分隐私与图像生成模型生成对抗网络（Generative adversarial network，GAN）相结合，提出了一种更具普适性的支持图像数据差分隐私保护的生成对抗网络模型（Image differential privacy-GAN，IDP-GAN）。 Aiming at the privacy leakage problem in the data mining model and the opacity of existing privacy protection technologies, a more universal image differential privacy-generative adversarial network(IDP-GAN) combining differential privacy with the image generation model—generative adversarial network(GAN) is proposed.
40085 IDP-GAN通过差分隐私的拉普拉斯实现机制，将拉普拉斯噪声合理地分配到判别器的仿射变换层的输入特征以及输出层的损失函数的多项式近似系数中。 IDP-GAN uses the Laplace implementation mechanism to reasonably allocate Laplace noise to the input features of the affine transformation layer and the polynomial approximation coefficients of the loss function of the output layer.