Research map / Image generation / Editing and style transfer
Conditional Score Guidance for Text-Driven Image-to-Image Translation
Hyunsoo Lee, Minsoo Kang, Bohyung Han
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add conditional score guidance (CSG w/o Mixup) over DDIM (ablation) | DDIM · cat -> dog | Structure Distance: 0.0725 -> 0.0199 | Improved |
| add conditional score guidance (CSG w/o Mixup) over DDIM (ablation) | DDIM · cat -> dog | Relational Distance: 0.4325 -> 0.0229 | Improved |
| add conditional score guidance (CSG w/o Mixup) over DDIM (ablation) | DDIM · zebra -> horse | Relational Distance: 0.8659 -> 0.1231 | Improved |
| add conditional score guidance (CSG w/o Mixup) over DDIM (ablation) | DDIM · dog -> dog w/ glasses | CLIP-similarity: 0.3139 -> 0.3238 | Improved |
| add conditional score guidance (CSG w/o Mixup) over DDIM (ablation) | DDIM · zebra -> horse | CLIP-similarity: 0.3006 -> 0.2916 | Hurt |
| add cross-attention mixup to CSG (ablation) | CSG · dog -> dog w/ glasses | Relational Distance: 0.0654 -> 0.0139 | Improved |
| add cross-attention mixup to CSG (ablation) | CSG · wolf -> lion | Relational Distance: 0.0829 -> 0.0778 | Improved |
| add cross-attention mixup to CSG (ablation) | CSG · cat -> dog | Structure Distance: 0.0199 -> 0.0192 | Improved |
| add cross-attention mixup to CSG (ablation) | CSG · cat -> dog | CLIP-similarity: 0.3008 -> 0.3014 | No clear effect |
| add cross-attention mixup to CSG (ablation) | CSG · cat -> dog | BG-LPIPS: 0.1896 -> 0.1867 | Improved |
| add cross-attention mixup to CSG (ablation) | CSG · wolf -> lion | BG-LPIPS: 0.2510 -> 0.2384 | Improved |
| CSG vs Pix2Pix-Zero | Pix2Pix-Zero · dog -> cat | Relational Distance: 0.3229 -> 0.0192 | Improved |
Closest papers by meaning
- R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation (ICLR 2024 · similarity 0.89)
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.88)
- Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion (CVPR 2025 · similarity 0.88)
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation (ICLR 2024 · similarity 0.88)
- Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis (CVPR 2025 · similarity 0.88)
- Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion (ICML 2024 · similarity 0.88)
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.
