Research map / Image generation / Editing and style transfer
Semantic Image Manipulation Using Scene Graphs
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 |
|---|---|---|---|
| Add visual feature encoding φᵢ (ablation) | Ours with CRN · Visual Genome image reconstruction (GT) | SSIM: 86.52 -> 88.29 | Helped |
| Add visual feature encoding φᵢ (ablation) | Ours with CRN · Visual Genome image reconstruction (GT) | MAE: 9.83 -> 7.43 | Helped |
| Add visual feature encoding φᵢ (ablation) | Ours with SPADE · Visual Genome image reconstruction (P) | SSIM: 84.61 -> 83.98 | Hurt |
| Use SPADE instead of CRN | Ours with GT scene graphs and visual features · CLEVR relationship changing, 64 × 64 | LPIPS: 0.0678 -> 0.069 | Mixed |
| Use the proposed reconstruction-trained method instead of fully supervised training | Image manipulation with CRN · CLEVR relationship changing, 64 × 64 | LPIPS: 0.111 -> 0.0678 | Helped |
Closest papers by meaning
- Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation (NeurIPS 2024 · similarity 0.88)
- Learning to Manipulate Artistic Images (AAAI 2024 · similarity 0.87)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.87)
- Scene Graph-Grounded Image Generation (AAAI 2025 · similarity 0.86)
- R3CD: Scene Graph to Image Generation with Relation-Aware Compositional Contrastive Control Diffusion (AAAI 2024 · similarity 0.85)
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models (CVPR 2024 · similarity 0.85)
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.