论文标题
对比单调像素级调制
Contrastive Monotonic Pixel-Level Modulation
论文作者
论文摘要
在低级视觉和神经图像翻译中，连续的一对多映射是一项较少调查但重要的任务。在本文中，我们提出了一种称为MonoPix的新配方，这是一个无监督和对比的连续调制模型，并进一步迈出了一个像素级的空间控制，这是至关重要的，但以前无法正确处理。这项工作的关键特征是使用新颖的对比度调制框架和相应的单调性约束对控制信号与域歧视器之间的单调性进行建模。我们还引入了具有对数近似复杂性的选择性推理策略，并支持快速域的适应性。在各种连续映射任务（包括AFHQ Cat-Dog和Yosemite夏季冬季翻译）上，对最新的性能进行了验证。引入的方法还有助于为许多低级任务（例如低光增强和自然噪声产生）提供新的解决方案，这超出了一对一训练和推理的长期实践。代码可从https://github.com/lukun199/monopix获得。
Continuous one-to-many mapping is a less investigated yet important task in both low-level visions and neural image translation. In this paper, we present a new formulation called MonoPix, an unsupervised and contrastive continuous modulation model, and take a step further to enable a pixel-level spatial control which is critical but can not be properly handled previously. The key feature of this work is to model the monotonicity between controlling signals and the domain discriminator with a novel contrastive modulation framework and corresponding monotonicity constraints. We have also introduced a selective inference strategy with logarithmic approximation complexity and support fast domain adaptations. The state-of-the-art performance is validated on a variety of continuous mapping tasks, including AFHQ cat-dog and Yosemite summer-winter translation. The introduced approach also helps to provide a new solution for many low-level tasks like low-light enhancement and natural noise generation, which is beyond the long-established practice of one-to-one training and inference. Code is available at https://github.com/lukun199/MonoPix.
