Research map / Image generation / GANs
Diverse Image Synthesis From Semantic Layouts via Conditional IMLE
Ke Li, Tianhao Zhang, Jitendra Malik
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 noise encoder (ablation) | conditional IMLE · GTA-5 diversity (LPIPS) | LPIPS diversity: 0.10 -> 0.19 | Improved |
| add dataset and loss rebalancing (ablation) | conditional IMLE · GTA-5 diversity (LPIPS) | LPIPS diversity: 0.17 -> 0.19 | Improved |
| add random noise input channels (ablation) | CRN · GTA-5 diversity (LPIPS) | LPIPS diversity: 0.11 -> 0.12 | Improved |
| replace CRN training with conditional IMLE (same architecture) (ablation) | CRN+noise · GTA-5 diversity (LPIPS) | LPIPS diversity: 0.12 -> 0.19 | Improved |
| add dataset and loss rebalancing (ablation) | CRN · GTA-5 diversity (LPIPS), with rebalancing | LPIPS diversity: 0.12 -> 0.13 | No clear effect |
| add dataset rebalancing (ablation) | Pix2pix-HD · GTA-5 diversity (LPIPS) | diversity | No clear effect |
| replace CRN with conditional IMLE (same architecture and distance metric) | CRN · GTA-5 human study (artifacts) | fraction with more synthetic patterns: 0.636 -> 0.364 | Improved |
Closest papers by meaning
- Semantic Probability Distribution Modeling for Diverse Semantic Image Synthesis (TPAMI 2022 · similarity 0.90)
- Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis (NeurIPS 2019 · similarity 0.90)
- Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation (IJCV 2020 · similarity 0.90)
- Diverse Semantic Image Synthesis via Probability Distribution Modeling (CVPR 2021 · similarity 0.90)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.88)
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · 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.
