Research map / Image generation / Editing and style transfer
IMAGINE: Image Synthesis by Image-Guided Model Inversion
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 image-guided classifier inversion with feature-distribution matching and adversarial patch training instead of DeepInversion | Image synthesis from a single reference image · Object images | IS: 68.5(5.0) -> 117.1(6.2) | Helped |
| Use image-guided classifier inversion with feature-distribution matching and adversarial patch training instead of DeepInversion | Image synthesis from a single reference image · Object images | FID: 65.9(2.7) -> 38.3(1.1) | Helped |
| Use image-guided classifier inversion with feature-distribution matching and adversarial patch training instead of DGP | Image synthesis from a single reference image · Scene images | IS: 12.7(0.6) -> 21.8(0.4) | Helped |
| Use image-guided classifier inversion with feature-distribution matching and adversarial patch training instead of DGP | Image synthesis from a single reference image · Scene images | FID: 51.3(1.6) -> 47.3(0.9) | Helped |
| Restrict feature matching to the three earliest layers, omitting the deepest layer (ablation) | IMAGINE · Object images | semantic consistency and image quality | Hurt |
| Use single-stage optimization with nonzero feature-matching and adversarial weights instead of the two-stage schedule (ablation) | IMAGINE · Image synthesis | image quality | No clear effect |
Closest papers by meaning
- You Only Need Adversarial Supervision for Semantic Image Synthesis (ICLR 2021 · similarity 0.88)
- Neural Photo Editing with Introspective Adversarial Networks (ICLR 2017 · similarity 0.88)
- Unlocking Pre-trained Image Backbones for Semantic Image Synthesis (CVPR 2024 · similarity 0.88)
- High Fidelity GAN Inversion via Prior Multi-Subspace Feature Composition (AAAI 2021 · similarity 0.88)
- Few-Shot Semantic Image Synthesis With Class Affinity Transfer (CVPR 2023 · similarity 0.87)
- ReMix: Towards Image-to-Image Translation With Limited Data (CVPR 2021 · 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.