Research map / Image generation / GANs
Image Synthesis From Reconfigurable Layout and Style
Wei Sun, Tianfu Wu
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 LostGAN instead of Layout2Im (64x64) | Layout2Im · COCO-Stuff layout-to-image | Inception score: 9.1 ± 0.1 -> 9.8 ± 0.2 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · Visual Genome layout-to-image | Inception score: 8.1 ± 0.1 -> 8.7 ± 0.4 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · COCO-Stuff layout-to-image | FID: 38.14 -> 34.31 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · Visual Genome layout-to-image | FID: 40.07 -> 34.75 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · COCO-Stuff layout-to-image | diversity score (LPIPS): 0.15 ± 0.06 -> 0.35 ± 0.09 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · Visual Genome layout-to-image | diversity score (LPIPS): 0.17 ± 0.09 -> 0.34 ± 0.10 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · COCO-Stuff layout-to-image | classification accuracy (CAS, %): 27.32 -> 28.81 | Improved |
| use LostGAN instead of Layout2Im (64x64) | Layout2Im · Visual Genome layout-to-image | classification accuracy (CAS, %): 23.25 -> 27.50 | Improved |
| raise output resolution from 64x64 to 128x128 | LostGAN · COCO-Stuff layout-to-image | FID: 34.31 -> 29.65 | Improved |
| raise output resolution from 64x64 to 128x128 | LostGAN · Visual Genome layout-to-image | classification accuracy (CAS, %): 27.50 -> 25.89 | Hurt |
| raise output resolution from 64x64 to 128x128 | LostGAN · COCO-Stuff layout-to-image | classification accuracy (CAS, %): 28.81 -> 28.70 | No clear effect |
Closest papers by meaning
- Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis (TPAMI 2021 · similarity 0.95)
- Interactive Image Synthesis With Panoptic Layout Generation (CVPR 2022 · similarity 0.89)
- Image Generation From Layout (CVPR 2019 · similarity 0.89)
- LayoutGAN: Synthesizing Graphic Layouts With Vector-Wireframe Adversarial Networks (TPAMI 2020 · similarity 0.89)
- StyleGAN2 Distillation for Feed-forward Image Manipulation (ECCV 2020 · similarity 0.88)
- Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020 · 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.
