论文标题
重新访问超分辨率中的L1损失：概率观点及以后
Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyond
论文作者
论文摘要
作为一个不良问题的超分辨率具有许多低分辨率输入的高分辨率候选者。但是，流行的$ \ ell_1 $损失用于最适合给定的人力资源图像，无法考虑图像恢复中非唯一性的基本属性。在这项工作中，我们通过用神经网络作为概率模型来制定超分辨率，以$ \ ell_1 $损失的方式修复了丢失的作品。它表明$ \ ell_1 $损失等于降低的似然函数，该功能从学习过程中消除了随机性。通过引入数据自适应随机变量，我们提出了一个新的目标函数，旨在最大程度地降低所有合理解决方案的重建误差的期望。实验结果表明，主流体系结构的一致改进，没有额外的参数或计算成本在推理时。
Super-resolution as an ill-posed problem has many high-resolution candidates for a low-resolution input. However, the popular $\ell_1$ loss used to best fit the given HR image fails to consider this fundamental property of non-uniqueness in image restoration. In this work, we fix the missing piece in $\ell_1$ loss by formulating super-resolution with neural networks as a probabilistic model. It shows that $\ell_1$ loss is equivalent to a degraded likelihood function that removes the randomness from the learning process. By introducing a data-adaptive random variable, we present a new objective function that aims at minimizing the expectation of the reconstruction error over all plausible solutions. The experimental results show consistent improvements on mainstream architectures, with no extra parameter or computing cost at inference time.
