Metraipolis › archive › dc_df26a1ae169e

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching — arXiv:2609.35673

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35673
License (as archived)
CC0-1.0
Archived
2026-10-07T23:54:55.268Z
SHA-256 of the archived text
e95a4a7dead7f6e3c334971ce7f95d9c6b31e243df99e1c78652898666f629a8
Stable URL of this page
https://metraipolis.com/documento/dc_df26a1ae169e

How to cite

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching — arXiv:2609.35673 — arXiv (en), https://arxiv.org/abs/2609.35673 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df26a1ae169e (Metraipolis archive dc_df26a1ae169e, sha256 e95a4a7dead7f6e3c334971ce7f95d9c6b31e243df99e1c78652898666f629a8)
BibTeX
@misc{dcdf26a1ae169e,
  title = {FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching — arXiv:2609.35673},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35673},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df26a1ae169e; sha256 e95a4a7dead7f6e3c334971ce7f95d9c6b31e243df99e1c78652898666f629a8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35673. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language models (MLLMs) that sequentially generate reasoning, tool selections, and parameter values. In this work, we present a novel approach to tool-based image editing by framing the task as a flow matching problem. We introduce FlowTool, a framework that directly models the distribution of high-quality tool parameters conditioned on the input image and user instruction using conditional rectified flow. FlowTool combines a vision-language model backbone for multimodal understanding with a Diffusion Transformer parameter generator that transforms Gaussian noise into an editing plan. We train FlowTool with a two-stage supervised flow-matching curriculum, followed by reward-based post-training. Across MMArt-Bench, FlowTool-Eval, ArtEdit-Bench, and MIT-Adobe5K, FlowTool achieves significantly stronger reference-based performance than specialized MLLM editing agents and proprietary MLLMs, while remaining competitive with proprietary models under reference-free evaluation. Moreover, FlowTool significantly improves inference efficiency, reducing latency by at least $50\times$ while requiring nearly $2\times$ less memory than the compared baselines. These results demonstrate that tool-based image editing can be effectively modeled as conditional generation over structured continuous editing parameters, without autoregressive reasoning.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35673 — 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 2026-10-07T23:29:27.616Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).