Metraipolis › archive › dc_8785bfdb83ce

Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation — arXiv:2609.22916

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22916
License (as archived)
CC0-1.0
Archived
2026-10-09T21:59:20.640Z
SHA-256 of the archived text
2a48ef31dc391244a9fee825564fe5045cdf328f5cb06d600b723055733c03ba
Stable URL of this page
https://metraipolis.com/documento/dc_8785bfdb83ce

How to cite

Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation — arXiv:2609.22916 — arXiv (en), https://arxiv.org/abs/2609.22916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8785bfdb83ce (Metraipolis archive dc_8785bfdb83ce, sha256 2a48ef31dc391244a9fee825564fe5045cdf328f5cb06d600b723055733c03ba)
BibTeX
@misc{dc8785bfdb83ce,
  title = {Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation — arXiv:2609.22916},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22916},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8785bfdb83ce; sha256 2a48ef31dc391244a9fee825564fe5045cdf328f5cb06d600b723055733c03ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit layout can provide structured guidance about what text should appear and where, but a well-formed plan alone does not guarantee that the renderer will realize it faithfully. Existing layout-based AR-diffusion systems typically optimize planning and rendering separately, preventing the planner's representations from being adapted jointly with image synthesis. We introduce DuetGen, an autonomous visual text generator built on DeepFusion, which jointly learns autoregressive planning and continuous diffusion rendering. DeepFusion conditions a diffusion transformer on the planner's prompt and bbox-content hidden states, allowing rendering supervision to shape the representations connecting textual plans with visual outputs. Its joint objective combines autoregressive plan supervision, text-region-weighted diffusion learning, and auxiliary coordinate supervision to maintain structured planning, emphasize text-bearing regions, and improve the spatial precision of planner representations. During inference, Phase-Aware Attention Modulation strengthens the correspondence between image regions and their matched coordinate and content states, facilitating region-specific execution of the generated plan. With a 2B planner and a 4B single-stream DiT, DuetGen achieves 0.8293 word accuracy on CVTG-2K and 0.938 accuracy on LongText-Bench, closely matching the substantially larger Qwen-Image on both benchmarks. These results demonstrate the value of jointly learned planning representations and region-specific rendering for autonomous visual text generation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.22916 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T21:45:20.827Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).