Research map / Image generation / Text-to-image diffusion
MetaPoint: Unlocking Precise Spatial Control in Visual Generation
Dewei Zhou, Xinyu Huang, Xun Wang, Ji Xie, Yabo Zhang, Liang Li, Kunchang Li, Zongxin Yang, Yi Yang
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 |
|---|---|---|---|
| replace text coordinates with MetaPoint 2D positional embeddings (ablation) | BAGEL · COCO-MIG | Instance Success Rate avg: 61.84 -> 84.72 | Improved |
| replace text coordinates with MetaPoint (ablation) | BAGEL · COCO-MIG | mIoU avg: 52.48 -> 77.29 | Improved |
| add MetaPoint to BAGEL | BAGEL · T2I-CoReBench | Overall: 38.2 -> 66.1 | Improved |
| add MetaPoint to BAGEL: reasoning | BAGEL · T2I-CoReBench Reasoning | Mean: +31.9 | Improved |
| add MetaPoint to BAGEL: composition | BAGEL · T2I-CoReBench Composition | Mean: +19.9 | Improved |
| add MetaPoint to BAGEL | BAGEL · ImgEdit | Overall: 3.42 -> 3.94 | Improved |
| add MetaPoint to BAGEL: Remove task | BAGEL · ImgEdit Remove | score: 3.16 -> 4.20 | Improved |
| add MetaPoint to BAGEL: Action task | BAGEL · ImgEdit Action | score: -0.03 | No clear effect |
| add MetaPoint to BAGEL on layout generation | BAGEL · COCO-MIG | Instance Success Rate avg: +18.28 vs SOTA | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- InstanceDiffusion — InstanceDiffusion: Instance-level Control for Image Generation (CVPR 2024) · better on 2 of 2 shared results
- MIGC — MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis (CVPR 2024) · better on 2 of 2 shared results
- OmniGen2-7B — OmniGen: Unified Image Generation (CVPR 2025) · better on 1 of 1 shared result
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
- Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models (NeurIPS 2026 · similarity 0.86)
- GenSpace: Benchmarking Spatially-Aware Image Generation (NeurIPS 2025 · similarity 0.86)
- SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent (NeurIPS 2025 · similarity 0.86)
- MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse (ICLR 2026 · similarity 0.85)
- VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis (AAAI 2025 · similarity 0.85)
- OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation (NeurIPS 2026 · 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.
