Research map / Image generation / Autoregressive and latent generation
Interactive Image Synthesis With Panoptic Layout Generation
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 PLG to CAL2I | CAL2I on COCO-Stuff with perturbed boxes · COCO-Stuff, Pert1 and Pert2 BBox | IS: 11.1±0.1 -> 13.2±0.2; 9.0±0.1 -> 11.7±0.2 | Helped |
| Add PLG to CAL2I | CAL2I on COCO-Stuff with perturbed boxes · COCO-Stuff, Pert1 and Pert2 BBox | FID: 43.12 -> 29.03; 57.89 -> 35.40 | Helped |
| Add PLG to CAL2I | CAL2I on Visual Genome with perturbed boxes · Visual Genome, Pert1 and Pert2 BBox | IS: 8.4±0.1 -> 10.6±0.1; 7.3±0.1 -> 10.1±0.1 | Helped |
| Add PLG to CAL2I | CAL2I on Visual Genome with perturbed boxes · Visual Genome, Pert1 and Pert2 BBox | FID: 49.53 -> 32.93; 61.30 -> 37.03 | Helped |
| Use PLGAN instead of Grid2Im | Landscape generation · Landscape 448×448 | FID: 144.84 -> 57.40 | Helped |
| Add PLG but omit ISA-Norm (ablation) | CAL2I · COCO-Stuff, GT BBox | IS: 15.6±0.2 -> 14.6±0.2 | Hurt |
| Add PLG but omit ISA-Norm (ablation) | CAL2I · COCO-Stuff, Pert1 and Pert2 BBox | IS: 11.1±0.1 -> 12.3±0.1; 9.0±0.1 -> 10.3±0.1 | Helped |
| Add ISA-Norm to PLG (ablation) | CAL2I+PLG · COCO-Stuff, Pert1 and Pert2 BBox | IS: 12.3±0.1 -> 13.9±0.2; 10.3±0.1 -> 12.8±0.2 | Helped |
| Add Guided Filter to ISA-Norm (ablation) | CAL2I+PLG+ISA-Norm · COCO-Stuff, Pert1 and Pert2 BBox | FID: 33.09 -> 27.03; 52.73 -> 33.40 | Helped |
| Use stuff layout alone instead of panoptic layout (ablation) | PLGAN · COCO-Stuff, GT BBox | FID: 22.70 -> 43.70 | Hurt |
| Use instance layout alone instead of panoptic layout (ablation) | PLGAN · COCO-Stuff, GT BBox | FID: 22.70 -> 24.15 | Hurt |
| Combine instance and stuff layouts (ablation) | PLGAN · COCO-Stuff, GT BBox | CAS: 32.52 -> 33.86 | Helped |
Closest papers by meaning
- LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators (ICLR 2019 · similarity 0.88)
- BachGAN: High-Resolution Image Synthesis From Salient Object Layout (CVPR 2020 · similarity 0.88)
- Object-Centric Image Generation from Layouts (AAAI 2021 · similarity 0.88)
- InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention (NeurIPS 2025 · similarity 0.86)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.86)
- StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN (CVPR 2024 · similarity 0.86)
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.