Research map / Image generation / Autoregressive and latent generation
Panoptic-Based Image Synthesis
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 panoptic-aware partial convolution to SPADE (ablation) | SPADE generator · Cityscapes | mIoU: 60.00 -> 61.24 | Helped |
| Add panoptic-aware partial convolution to SPADE (ablation) | SPADE generator · Cityscapes | detAP: 10.97 -> 11.50 | Helped |
| Add panoptic-aware upsampling after panoptic-aware partial convolution (ablation) | SPADE generator · Cityscapes | mIoU: 61.24 -> 64.55 | Helped |
| Add panoptic-aware upsampling after panoptic-aware partial convolution (ablation) | SPADE generator · Cityscapes | detAP: 11.50 -> 13.04 | Helped |
| Replace SPADE with the full panoptic-based generator | SPADE · Cityscapes | FID: 71.8 -> 96.4 | Hurt |
| Replace SPADE with the full panoptic-based generator | SPADE · COCO-Stuff | FID: 22.6 -> 28.8 | Hurt |
Closest papers by meaning
- Diverse Semantic Image Synthesis via Probability Distribution Modeling (CVPR 2021 · similarity 0.88)
- Interactive Image Synthesis With Panoptic Layout Generation (CVPR 2022 · similarity 0.87)
- Semantic Image Synthesis With Spatially-Adaptive Normalization (CVPR 2019 · similarity 0.87)
- 3D-Aware Conditional Image Synthesis (CVPR 2023 · similarity 0.87)
- Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis (CVPR 2025 · similarity 0.85)
- VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis (CVPR 2026 · 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.