What question did this study set out to answer?

This survey aims to review and critically analyze the progress of generative adversarial networks in computer vision applications. It addresses key challenges such as image quality, diversity, and training stability.

June 4, 2019Open Access

Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy

View Full Paper

Ask AI

Bookmark

Authors

ZWZhengwei WangDongshin University QSQi SheIntel (United States)TWTomás WardDublin City University

Discussion

Member takes

Implication

Survey analyzes generative adversarial networks’ impact on computer vision applications, highlighting challenges and advances.

Key Points

This survey aims to review and critically analyze the progress of generative adversarial networks in computer vision applications. It addresses key challenges such as image quality, diversity, and training stability.
Conducted a detailed literature review of GAN-related research focused on major challenges.
Structured the review using a taxonomy based on variations in GAN architectures and loss functions.
Discussed applications of GANs and proposed future research directions.
Identified significant advances in GAN technologies, particularly in image generation and manipulation.
Highlighted persistent challenges including producing high-quality images and ensuring diverse outputs.
Critically discussed the state of various GAN architectures and their effectiveness in addressing practical computer vision issues.

Cite This Study

Wang et al. (2019) studied this question.

synapsesocial.com/papers/6a0eb55d06ecbe833447b910 https://doi.org/10.48550/arxiv.1906.01529

View Full Paper

Ask AI

Bookmark

Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy

Discussion

Member takes

Implication

Key Points

Cite This Study

Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider