Metraipolis › archive › dc_bc861260857a

Rethinking Camouflage Image Generation towards a Training-Free Paradigm — arXiv:2609.14377

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14377
License (as archived)
CC0-1.0
Archived
2026-10-16T01:53:00.044Z
SHA-256 of the archived text
896a243976e1feb84bf10d3334fa6ad6e54b2bc84a352ffb9e00297a50a2c73e
Stable URL of this page
https://metraipolis.com/documento/dc_bc861260857a

How to cite

Rethinking Camouflage Image Generation towards a Training-Free Paradigm — arXiv:2609.14377 — arXiv (en), https://arxiv.org/abs/2609.14377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc861260857a (Metraipolis archive dc_bc861260857a, sha256 896a243976e1feb84bf10d3334fa6ad6e54b2bc84a352ffb9e00297a50a2c73e)
BibTeX
@misc{dcbc861260857a,
  title = {Rethinking Camouflage Image Generation towards a Training-Free Paradigm — arXiv:2609.14377},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14377},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc861260857a; sha256 896a243976e1feb84bf10d3334fa6ad6e54b2bc84a352ffb9e00297a50a2c73e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background contexts. Achieving this objective requires jointly satisfying three coupled requirements: foreground preservation to retain target integrity, semantic compatibility to select plausible concealment contexts, and appearance assimilation to reduce visual discrepancies. Recent approaches predominantly rely on task-specific training on camouflage datasets to address these requirements, incurring substantial computational cost and limiting generalization beyond the training domain. To address these limitations, we formulate training-free CIG as a concealment-oriented paradigm that preserves the target while reducing its perceptual separability from the synthesized surroundings, rather than maintaining its visual prominence, without parameter updates. We instantiate this paradigm with FreeCam based on a frozen inpainting diffusion framework to preserve the foreground. Within this framework, a Contextual Reasoning Module exploits frozen multimodal priors to infer an environment favorable to concealment, thereby promoting semantic compatibility, while an Intrinsic Appearance Module extracts low-level color and texture cues from the foreground to guide background synthesis toward appearance assimilation. Extensive experiments demonstrate that FreeCam achieves state-of-the-art generation quality and camouflage effectiveness without task-specific training, while its generated images provide synthetic supervision for camouflaged object detection and reduce target detectability under general object detectors.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.14377 — 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 2026-10-16T01:25:23.576Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).