IEEE Trans Cybern. 2018 Apr;48(4):1189-1201. doi: 10.1109/TCYB.2017.2682853. Epub 2017 May 2.
Recently, locality-constrained linear coding (LLC) has been drawn great attentions and been widely used in image processing and computer vision tasks. However, the conventional LLC model is always fragile to outliers. In this paper, we present a robust locality-constrained bi-layer representation model to simultaneously hallucinate the face images and suppress noise and outliers with the assistant of a group of training samples. The proposed scheme is not only able to capture the nonlinear manifold structure but also robust to outliers by incorporating a weight vector into the objective function to subtly tune the contribution of each pixel offered in the objective. Furthermore, a high-resolution (HR) layer is employed to compensate the missed information in the low-resolution (LR) space for coding. The use of two layers (the LR layer and the HR layer) is expected to expose the complicated correlation between the LR and HR patch spaces, which helps to obtain the desirable coefficients to reconstruct the final HR face. The experimental results demonstrate that the proposed method outperforms the state-of-the-art image super-resolution methods in terms of both quantitative measurements and visual effects.
近年来，局部约束线性编码 (LLC) 引起了广泛关注，并在图像处理和计算机视觉任务中得到了广泛应用。然而，传统的 LLC 模型对外点很敏感。在本文中，我们提出了一种鲁棒的局部约束双层表示模型，该模型利用一组训练样本同时对人脸图像进行幻觉和抑制噪声和外点。所提出的方案不仅能够捕获非线性流形结构，而且通过在目标函数中引入权向量来稳健地处理外点，从而巧妙地调整目标中每个像素的贡献。此外，还使用了一个高分辨率 (HR) 层来补偿低分辨率 (LR) 空间中的丢失信息，以进行编码。使用两层（LR 层和 HR 层）有望揭示 LR 和 HR 补丁空间之间的复杂相关性，这有助于获得理想的系数来重建最终的 HR 人脸。实验结果表明，所提出的方法在定量测量和视觉效果方面均优于最先进的图像超分辨率方法。
