Research map / Image generation / GANs
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
Read the paperCheck 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 CC-FPSE instead of SPADE | Semantic image synthesis · COCO-Stuff | mIOU: 37.4 -> 41.6 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · COCO-Stuff | Accu: 67.9 -> 70.7 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · COCO-Stuff | FID: 22.6 -> 19.2 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · Cityscapes | mIOU: 62.3 -> 65.5 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · Cityscapes | Accu: 81.9 -> 82.3 | Helped |
| Use CC-FPSE instead of SIMS | Semantic image synthesis · Cityscapes | FID: 49.7 -> 54.3 | Hurt |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · ADE20K | mIOU: 38.5 -> 43.7 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · ADE20K | Accu: 79.9 -> 82.9 | Helped |
| Use CC-FPSE instead of SPADE | Semantic image synthesis · ADE20K | FID: 33.9 -> 31.7 | Helped |
| Replace SPADE generator with conditional convolution generator (ablation) | SPADE baseline with MsPatch discriminator · COCO-Stuff | mIOU: 35.2 -> 36.2 | Helped |
| Add feature pyramid structure to the CC weight prediction network (ablation) | CC generator with MsPatch discriminator · COCO-Stuff | mIOU: 36.2 -> 36.7 | Helped |
| Add semantics embedding to the discriminator (ablation) | CC generator with feature pyramid weight prediction · COCO-Stuff | mIOU: 36.7 -> 40.4 | Helped |
Closest papers by meaning
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.93)
- You Only Need Adversarial Supervision for Semantic Image Synthesis (ICLR 2021 · similarity 0.91)
- Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis (ICLR 2023 · similarity 0.91)
- Semantic Pyramid for Image Generation (CVPR 2020 · similarity 0.91)
- Semantic Palette: Guiding Scene Generation With Class Proportions (CVPR 2021 · similarity 0.91)
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 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.