Improving Complex Scene Generation by Enhancing Multi-scale Representations of GAN Discriminators

Improving Complex Scene Generation by Enhancing Multi-scale Representations of GAN Discriminators

While recent advances of GAN models enabled photo-realistic synthesis of various object images, challenges still remain in modeling more complex image distributions such as scenes with multiple objects. The difficulty lies in the high structural complexity of scene images, where the discriminator ca...

Full description

Bibliographic Details
Main Authors: Lee, H. (Author), Lee, S. (Author), Park, J. (Author), Shim, J. (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2023
Subjects:
Complex networks
Complex scenes
Discriminators
Feature extraction
Features extraction
Generative adversarial networks
Generative Adversarial Networks
Generator
Generators
Image enhancement
Job analysis
Personnel training
Scene generation
Scene Generation
Scene image
Self-supervised learning
Self-Supervised Learning
Supervised learning
Task analysis
Training
Transfer learning
Transfer Learning
Online Access:View Fulltext in Publisher
View in Scopus

Similar Items

Similar Items