Recent image-to-image translation models have shown great success in mapping local textures between two domains. Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping. However, learning the inverse mapping introduces extra trainable parameters and it is unable to learn the inverse mapping for some domains. As a result, they are ineffective in the scenarios where (i) multiple visual image domains are involved; (ii) both structure and texture transformations are required; and (iii) semantic consistency is preserved. To solve these challenges, the paper proposes a unified model to translate images across multiple domains with significant domain gaps. Unlike previous models that constrain the generators with the ubiquitous cycle-consistency constraint to achieve the content similarity, the proposed model employs a perceptual self-regularization constraint. With a single unified generator, the model can maintain consistency over the global shapes as well as the local texture information across multiple domains. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and superior performance over state-of-the-art models. It is more effective in representing shape deformation in challenging mappings with significant dataset variation across multiple domains.
翻译:最近的图像到图像翻译模型在绘制两个领域之间的本地纹理方面显示出巨大的成功。 现有方法依赖于循环一致性限制, 以监督生成者学习反向映射。 但是, 学习反向映射引入了额外的可培训参数, 无法对某些领域进行反向映射。 因此, 在涉及多个视觉图像域的假设情景中, 这些模型是无效的, (一) 涉及多个视觉图像域;(二) 需要结构和纹理转换;(三) 保持语义一致性。 为应对这些挑战,本文件提出了一个统一模型, 用于翻译具有显著域间差距的多个域的图像。 与以往限制生成者实现内容相似性的周期一致性约束模型不同, 拟议的模型采用了一种概念性自我常规化的制约。 有了单一的统一生成器, 模型可以保持全球形状的一致性, 以及跨多个域的本地纹理信息。 广泛的定性和定量评估表明, 相对于状态模型而言, 效果和优异性表现。 它与以往限制生成者以普遍存在的周期一致性的形状不同, 在具有挑战性、数据变化的多个区域中, 比较有效。