Image synthesis method based on multiple text description
Aiming at the challenges associates with the low quality and structural errors existed in the images generated by a single text description, a multi-stage generative adversarial network model was used to study, and it was proposed to interpolate different text sequences to enrich the given text desc...
Saved in:
Main Authors: | NIE Kaiqin, NI Zhengwei |
---|---|
Format: | Article |
Language: | zho |
Published: |
Beijing Xintong Media Co., Ltd
2024-05-01
|
Series: | Dianxin kexue |
Subjects: | |
Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2024142/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
High-Quality Text-to-Image Generation Using High-Detail Feature-Preserving Network
by: Wei-Yen Hsu, et al.
Published: (2025-01-01) -
DADNet: text detection of arbitrary shapes from drone perspective based on boundary adaptation
by: Jun Liu, et al.
Published: (2024-11-01) -
Semantic Image Synthesis via Class-Adaptive Cross-Attention
by: Tomaso Fontanini, et al.
Published: (2025-01-01) -
Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis
by: Qifeng Liu, et al.
Published: (2025-01-01) -
Noise Robust Underwater Fishing Net Recognition Based on Range Gated Imaging
by: Zhensong Xu, et al.
Published: (2024-01-01)