Research map / Image generation / Editing and style transfer
Semantic Image Synthesis With Spatially-Adaptive Normalization
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 SPADE instead of the corresponding non-SPADE strong baseline (ablation) | pix2pixHD++ · semantic image synthesis benchmarks | performance | Helped |
| Replace SPADE with segmentation-mask feature concatenation at intermediate layers (ablation) | pix2pixHD++ · semantic image synthesis benchmarks | performance | Hurt |
| Use random noise rather than a downsampled segmentation map as generator input (ablation) | SPADE generator · semantic image synthesis | performance | No clear effect |
| Vary the parameter-free normalization layer before SPADE modulation (ablation) | SPADE generator · semantic image synthesis | performance | No clear effect |
| Use a 1x1 convolutional kernel on the label map (ablation) | SPADE generator · semantic image synthesis | performance | Hurt |
| Vary the number of convolutional filters (ablation) | SPADE generator · semantic image synthesis | performance | Mixed |
| Remove the perceptual loss (ablation) | SPADE training objective · semantic image synthesis | performance | Hurt |
| Remove the GAN feature matching loss (ablation) | SPADE training objective · semantic image synthesis | performance | Hurt |
| Add one convolutional layer to deepen the discriminator (ablation) | pix2pixHD discriminator · semantic image synthesis | performance | No clear effect |
| Add spectral normalization (ablation) | pix2pixHD++ · semantic image synthesis | performance | Helped |
| Add synchronized BatchNorm (ablation) | pix2pixHD++ · semantic image synthesis | performance | Helped |
| Use TTUR (ablation) | pix2pixHD++ · semantic image synthesis | performance | Helped |
Closest papers by meaning
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · similarity 0.90)
- Retrieval-Based Spatially Adaptive Normalization for Semantic Image Synthesis (CVPR 2022 · similarity 0.90)
- SEAN: Image Synthesis With Semantic Region-Adaptive Normalization (CVPR 2020 · similarity 0.89)
- Diverse Semantic Image Synthesis via Probability Distribution Modeling (CVPR 2021 · similarity 0.89)
- Control and Realism: Best of Both Worlds in Layout-to-Image without Training (ICML 2025 · similarity 0.88)
- STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis (NeurIPS 2025 · similarity 0.86)
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.