Research map / Image generation / Text-to-image diffusion
PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models
Runze He, Bo Cheng, Yuhang Ma, Qingxiang Jia, Shanyuan Liu, Ao Ma, Xiaoyu Wu, Liebucha Wu, Dawei Leng, Yuhui Yin
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 |
|---|---|---|---|
| encode numbers as normal text instead of special tokens (ablation) | PlanGen · Ablation (training subset), layout-to-image | Spatial: 81.94 -> 87.52 | Improved |
| encode numbers as normal text instead of special tokens (ablation) | PlanGen · Ablation (training subset), layout-to-image | Color: 59.61 -> 68.14 | Improved |
| add image layout understanding task to LIG+LP training (ablation) | PlanGen · Ablation (training subset), layout-to-image | Spatial: 83.25 -> 87.52 | Improved |
| add layout planning task to layout-to-image training (ablation) | PlanGen · Ablation (training subset), layout-to-image | Color: 72.25 -> 69.46 | Hurt |
| multi-task training with all tasks vs layout-to-image alone (ablation) | PlanGen · Ablation (training subset), layout-to-image | Spatial: 87.19 -> 87.52 | No clear effect |
| add negative layout guidance (ablation) | PlanGen · Object removal | SR: 77.50 -> 86.50 | Improved |
| add negative layout guidance (ablation) | PlanGen · Object removal | LocalCLIP: 21.96 -> 21.90 | No clear effect |
Later papers that compared with this method
3 later accepted papers report PlanGen as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding (AAAI 2026 · better on 8 of 9 shared results)
- Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking (ECCV 2026 · better on 6 of 7 shared results)
- ConsistCompose: Unified Multimodal Layout Control for Image Composition (CVPR 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HiCo — HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation (NeurIPS 2024) · better on 5 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LayoutGPT: Compositional Visual Planning and Generation with Large Language Models (NeurIPS 2023 · similarity 0.90)
- Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models (NeurIPS 2026 · similarity 0.90)
- Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation (NeurIPS 2024 · similarity 0.89)
- InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention (NeurIPS 2025 · similarity 0.87)
- SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation (AAAI 2024 · similarity 0.87)
- LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models (CVPR 2025 · 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.
