重新思考伪装图像生成：迈向免训练范式
Rethinking Camouflage Image Generation towards a Training-Free Paradigm
浏览论文内容
中文总结 AI 辅助
本文提出免训练的伪装图像生成范式FreeCam，基于冻结修复扩散框架，通过上下文推理与内在外观模块实现前景保持、语义兼容和外观同化，无需任务特定训练即可达到最先进生成质量与伪装效果。
中文摘要 AI 辅助
伪装图像生成（CIG）旨在通过将前景对象融入与隐蔽性兼容的背景环境中，合成逼真的伪装图像。实现这一目标需要同时满足三个耦合要求：前景保持以保留目标完整性、语义兼容性以选择合理的隐蔽环境，以及外观同化以减少视觉差异。近期方法主要依赖在伪装数据集上进行任务特定训练来满足这些要求，这带来了高昂的计算成本，并限制了在训练领域之外的泛化能力。为解决这些局限，我们将免训练CIG构建为一种面向隐蔽的范式，在无需参数更新的情况下，保留目标的同时降低其与合成周围环境的感知可分离性，而非维持其视觉显著性。我们基于冻结的修复扩散框架，用FreeCam实例化该范式以保留前景。在该框架内，上下文推理模块利用冻结的多模态先验来推断有利于隐蔽的环境，从而促进语义兼容性；而内在外观模块则从前景中提取低层颜色和纹理线索，引导背景合成实现外观同化。大量实验表明，FreeCam无需任务特定训练即可达到最先进的生成质量和伪装效果，同时其生成的图像为伪装目标检测提供合成监督，并降低目标在通用目标检测器下的可检测性。
英文摘要
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.
发表机构
- Northwestern Polytechnical University（西北工业大学）
机构由 AI 辅助整理，请以论文原文为准。
