Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. However, their used constraints for pluralistic image completion are argued to be not well interpretable and unsatisfactory from two aspects. First, the constraints for visual reality can be weakly correlated to the objective of image completion or even redundant. Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well. In this paper, to address the issues, we propose an end-to-end probabilistic method. Specifically, we introduce a unified probabilistic graph model that represents the complex interactions in image completion. The entire procedure of image completion is then mathematically divided into several sub-procedures, which helps efficient enforcement of constraints. The sub-procedure directly related to pluralistic results is identified, where the interaction is established by a Gaussian mixture model (GMM). The inherent parameters of GMM are task-related, which are optimized adaptively during training, while the number of its primitives can control the diversity of results conveniently. We formally establish the effectiveness of our method and demonstrate it with comprehensive experiments.
翻译:多元图像的完成侧重于为图像的完成产生视觉现实和多样化的结果。 先前的方法享有这项任务的经验性成功。 但是,它们对于多元图像的完成所使用的限制从两个方面来看是不完全可以解释的,不尽人意的。 首先,视觉现实的限制因素可能与图像完成的目标关系不大,甚至多余。 其次,多样性的限制因素设计成任务不可知性,这给效果不好造成了制约。 在本文件中,为了解决问题,我们建议了一个端到端的概率性方法。 具体地说,我们引入了一个代表图像完成中复杂互动的统一概率图形模型。 然后,图像完成的整个程序从数学上分为几个子程序,这有助于有效强制执行限制。 我们正式确定了与多元结果直接相关的次级程序,这些互动是由高斯混合模型(GMMM)建立的。 GMM的固有参数与任务有关,在培训期间最优化了任务相关参数,而其原始数字可以控制结果的多样性。 我们正式确定了我们方法的有效性,并以全面试验的形式展示了它。