Research map / Image generation / Text-to-image diffusion
CookGAN: Causality Based Text-to-Image Synthesis
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 CookGAN's causal, stepwise recipe-to-image generation instead of StackGAN++ | Recipe1M image generation · Recipe1M test | Inception score: 5.03 ± .09 -> 5.41 ± .11 | Helped |
| add cooking-step encoding with the Cooking Simulator (ablation) | CookGAN · Recipe1M test | Inception score: 4.79 ± .08 -> 5.41 ± .11 | Helped |
| add image-attended ingredient features during sequential upsampling (ablation) | CookGAN · Recipe1M test | Inception score: 5.30 ± .09 -> 5.41 ± .11 | Helped |
| add cooking-step encoding with the Cooking Simulator (ablation) | CookGAN · Recipe1M test, I2R | MedR: 84.5 -> 64.0 | Helped |
| add image-attended ingredient features during sequential upsampling (ablation) | CookGAN · Recipe1M test, I2R | MedR: 77.0 -> 64.0 | Helped |
| add cooking-step encoding with the Cooking Simulator (ablation) | CookGAN · Recipe1M test, I2I | MedR: 115.5 -> 108.0 | Helped |
| add image-attended ingredient features during sequential upsampling (ablation) | CookGAN · Recipe1M test, I2I | MedR: 123.0 -> 108.0 | Helped |
| progressively upsample recipe-conditioned images rather than use R2GAN thumbnails | Recipe1M image generation and I2R retrieval · Recipe1M test, I2R | MedR: 500.0 -> 64.0 | Helped |
| add ingredients and cooking instructions together rather than use ingredients alone (ablation) | CookGAN · Recipe1M test | Inception score: 4.79 ± .08 -> 5.41 ± .11 | Helped |
Closest papers by meaning
- Inverse Cooking: Recipe Generation From Food Images (CVPR 2019 · similarity 0.89)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.85)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.83)
- Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective (ICLR 2025 · similarity 0.83)
- Image Content Generation with Causal Reasoning (AAAI 2024 · similarity 0.82)
- VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis (AAAI 2025 · similarity 0.82)
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.