Research map / Image generation / Editing and style transfer
ManiGAN: Text-Guided Image Manipulation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ManiGAN instead of SISGAN or TAGAN | text-guided image manipulation · CUB | MP: .022 -> .072 | Helped |
| Use ManiGAN instead of SISGAN or TAGAN | text-guided image manipulation · COCO | MP: .042 -> .068 | Helped |
| Add ACM and DCM rather than removing both and concatenating features only at the start (ablation) | ManiGAN · CUB | IS: 4.01 -> 8.47 | Helped |
| Add ACM and DCM rather than removing both and concatenating features only at the start (ablation) | ManiGAN · COCO | MP: .056 -> .068 | Helped |
| Use ACM instead of concatenation (ablation) | ManiGAN · CUB | MP: .065 -> .072 | Helped |
| Use ACM instead of concatenation (ablation) | ManiGAN · COCO | MP: .039 -> .068 | Helped |
| Add the main module rather than train DCM only (ablation) | ManiGAN · CUB | MP: .064 -> .072 | Helped |
| Add the main module rather than train DCM only (ablation) | ManiGAN · COCO | MP: .066 -> .068 | Helped |
| Add DCM (ablation) | ManiGAN · CUB | MP: .068 -> .072 | Helped |
| Add DCM (ablation) | ManiGAN · COCO | IS: 6.99 -> 14.96 | Helped |
| Add the main module rather than train DCM only (ablation) | ManiGAN · CUB | IS: 8.48 -> 8.47 | No clear effect |
| Add the main module rather than train DCM only (ablation) | ManiGAN · COCO | IS: 17.59 -> 14.96 | Hurt |
Closest papers by meaning
- Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language (NeurIPS 2018 · similarity 0.91)
- Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation (NeurIPS 2020 · similarity 0.91)
- TiGAN: Text-Based Interactive Image Generation and Manipulation (AAAI 2022 · similarity 0.90)
- ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-Wise Semantic Alignment and Generation (CVPR 2022 · similarity 0.89)
- DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR 2022 · similarity 0.88)
- Prompt Augmentation for Self-supervised Text-guided Image Manipulation (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.