Research map / Image generation / Autoregressive and latent generation
StoryGAN: A Sequential Conditional GAN for Story Visualization
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 the full StoryGAN rather than independent image generation | StoryGAN · CLEVR-SV test | SSIM: 0.596 -> 0.672 | Helped |
| Replace Text2Gist with simple concatenation (ablation) | StoryGAN · CLEVR-SV test | SSIM: 0.672 -> 0.641 | Hurt |
| Replace Text2Gist with a filter network applied to the initial story encoding (ablation) | StoryGAN · CLEVR-SV test | SSIM: 0.672 -> 0.654 | Hurt |
| Remove the story discriminator, story encoder, and Context Encoder, and generate images independently (ablation) | StoryGAN · CLEVR-SV test | SSIM: 0.672 -> 0.596 | Hurt |
| Use the full StoryGAN rather than independent image generation | StoryGAN · Pororo-SV test | character classification accuracy: 0.23 -> 0.27 | Helped |
| Replace Text2Gist with simple concatenation (ablation) | StoryGAN · Pororo-SV test | character classification accuracy: 0.27 -> 0.21 | Hurt |
| Replace Text2Gist with a filter network applied to the initial story encoding (ablation) | StoryGAN · Pororo-SV test | character classification accuracy: 0.27 -> 0.24 | Hurt |
| Remove the sequential context components and generate images independently (ablation) | StoryGAN · Pororo-SV test | character classification accuracy: 0.27 -> 0.23 | Hurt |
| Use StoryGAN instead of ImageGAN | Story visualization models · Pororo-SV human evaluation | consistency preference: 15.28 -> 79.15 | Helped |
| Initialize the recurrent context cell with the Story Encoder output instead of random initialization (ablation) | StoryGAN · Pororo-SV | first-image quality | Helped |
| Use the two-level discriminator and recurrent input structure to preserve sequence consistency (ablation) | StoryGAN · CLEVR-SV | story consistency | Helped |
Closest papers by meaning
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.91)
- Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models (CVPR 2024 · similarity 0.89)
- Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models (AAAI 2025 · similarity 0.88)
- ViStoryBench: Comprehensive Benchmark Suite for Story Visualization (CVPR 2026 · similarity 0.88)
- Storybooth: Training-Free Multi-Subject Consistency for Improved Visual Storytelling (ICLR 2025 · similarity 0.87)
- ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context (AAAI 2025 · similarity 0.87)
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.