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
-
Exploring Progress in Text-to-Image Synthesis: An In-Depth Survey on the Evolution of Generative Adversarial Networks
by: Md Ahsan Habib, et al.
Published: (2024-01-01) -
TEXT DESCRIPTION TO IMAGE GENERATION USING GENERATIVE ADVERSARIAL NETWORK
by: Kayal Padmanandam, et al.
Published: (2024-12-01) -
Novel cross-dimensional coarse-fine-grained complementary network for image-text matching
by: Meizhen Liu, et al.
Published: (2025-03-01) -
Dual conditional GAN based on external attention for semantic image synthesis
by: Gang Liu, et al.
Published: (2023-12-01) -
Self-Attention-Based Text Encoder for Enhancing DMGAN Text-to-Image Generation
by: Remya Gopalakrishnan, et al.
Published: (2025-01-01)