High-Quality Text-to-Image Generation Using High-Detail Feature-Preserving Network
Multistage text-to-image generation algorithms have shown remarkable success. However, the images produced often lack detail and suffer from feature loss. This is because these methods mainly focus on extracting features from images and text, using only conventional residual blocks for post-extracti...
Saved in:
Main Authors: | Wei-Yen Hsu, Jing-Wen Lin |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/15/2/706 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Disentangled Contrastive Learning From Synthetic Matching Pairs for Targeted Chest X-Ray Generation
by: Euyoung Kim, et al.
Published: (2025-01-01) -
Tea Disease Recognition Based on Image Segmentation and Data Augmentation
by: Ji Li, et al.
Published: (2025-01-01) -
A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation
by: Xiurong Zhang, et al.
Published: (2024-12-01) -
Remote sensing image dehazing using a wavelet-based generative adversarial networks
by: Guangda Chen, et al.
Published: (2025-01-01) -
GENERATIONAL CLASSIFIER OF MODERN RUSSIAN SOCIETY
by: A. V. Milekhin, et al.
Published: (2021-02-01)