Research map / Image generation / Autoregressive and latent generation
Semi-Parametric Image Synthesis
Xiaojuan Qi, Qifeng Chen, Jiaya Jia, Vladlen Koltun
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 |
|---|---|---|---|
| Use retrieved image segments and a synthesis network instead of Pix2pix | Semantic-layout image synthesis · Cityscapes-coarse, Cityscapes-fine, Cityscapes→GTA5, NYU, ADE20K | A/B preference rate: 94.2%; 98.1%; 95.7%; 94.9%; 87.6% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · Cityscapes-coarse, Cityscapes-fine, Cityscapes→GTA5, NYU, ADE20K | A/B preference rate: 93.9%; 74.1%; 84.5%; 89.1%; 88.9% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · Cityscapes-coarse | IoU: 28.5% -> 56.3% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · Cityscapes-coarse | pixel accuracy: 36.2% -> 65.6% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · Cityscapes-fine | IoU: 51.3% -> 51.4% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · Cityscapes-fine | pixel accuracy: 61.4% -> 65.5% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · ADE20K | IoU: 23.1% -> 38.4% | Improved |
| Use retrieved image segments and a synthesis network instead of CRN | Semantic-layout image synthesis · ADE20K | pixel accuracy: 30.7% -> 50.1% | Improved |
Closest papers by meaning
- Photographic Image Synthesis With Cascaded Refinement Networks (ICCV 2017 · similarity 0.90)
- Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis (NeurIPS 2019 · similarity 0.88)
- Image Synthesis via Semantic Composition (ICCV 2021 · similarity 0.88)
- PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis (CVPR 2024 · similarity 0.86)
- SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow (NeurIPS 2024 · similarity 0.85)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (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.
