Timezone: »

Pluralistic Image Completion with Gaussian Mixture Models
Xiaobo Xia · Wenhao Yang · Jie Ren · Yewen Li · Yibing Zhan · Bo Han · Tongliang Liu

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #212

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. The implementationis available at https://github.com/tmllab/PICMM.

Author Information

Xiaobo Xia (The University of Sydney)
Wenhao Yang (Nanjing University)
Jie Ren (University of Edinburgh, University of Edinburgh)
Yewen Li (nanyang technological university)
Yibing Zhan (JD Explore Academy)
Tongliang Liu (The University of Sydney)

More from the Same Authors