Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions. Yet, the dominant paradigm is to employ pixel-wise losses, such as L_1, which drive the prediction towards a blurry average. This leads to fundamentally conflicting objectives when combined with adversarial losses, which degrades the final quality. We address this issue by revisiting the L_1 loss and show that it corresponds to a one-layer conditional flow. Inspired by this relation, we explore general flows as a fidelity-based alternative to the L_1 objective. We demonstrate that the flexibility of deeper flows leads to better visual quality and consistency when combined with adversarial losses. We conduct extensive user studies for three datasets and scale factors, where our approach is shown to outperform state-of-the-art methods for photo-realistic super-resolution. Code and trained models will be available at: git.io/AdFlow

翻译：超级分辨率是一个错误的问题, 地面真实高分辨率图像在合理解决方案的空间中仅代表一种可能性。 然而, 主导范例是使用像素损失, 如L_ 1, 这使得预测达到模糊平均值。 当与对抗性损失相结合, 从而降低最终质量时, 这会导致根本上的冲突目标。 我们通过重新审视 L_ 1 损失来解决这个问题, 并显示它与一层有条件流动相对应。 受此关系的影响, 我们探索一般流动, 将其作为基于忠诚的替代L_ 1 目标的替代物。 我们证明, 更深层流动的灵活性在与对抗性损失相结合时会提高视觉质量和一致性。 我们为三种数据集和规模因素进行广泛的用户研究, 显示我们的方法优于光现实性超级分辨率的最新方法。 代码和经过训练的模型将在以下提供: git.io/ AdFlow 。