Manifold-valued image generation with Wasserstein generative adversarial nets

• Main Authors: HUANG, Zhiwu, WU J., VAN, G. L.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Benchmark datasets; Complete manifold; Data distribution; Hue saturation values; Image generations; Machine learning problem; Optimal transport; Wasserstein distance; Artificial Intelligence and Robotics; OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/6546; https://ink.library.smu.edu.sg/context/sis_research/article/7549/viewcontent/Manifold_valued_image_generation_with_Wasserstein_generative_adversarial_nets.pdf
• Institution: Singapore Management University

Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fil...