面向下一规模自回归文本图像编辑的离散噪声反转
Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
AI总结：
该研究提出专为视觉自回归模型（VAR）设计的基于噪声反转的图像编辑技术VARIN，通过位置感知Argmax反转生成逆Gumbel噪声，实现无需额外训练的可控文本引导图像编辑，且能较好保留原图背景与结构细节。
摘要：
视觉自回归模型（Visual autoregressive models, VAR）近期成为一类颇具前景的生成模型，在文本生成图像任务中取得了与扩散模型相当的性能。尽管条件生成已被广泛研究，但无需额外训练即可实现提示引导的图像编辑能力同样至关重要，它可支撑众多实际的现实应用。本文通过提出视觉自回归逆噪声（Visual AutoRegressive Inverse Noise, VARIN）——首个专为VAR模型设计的基于噪声反转的编辑技术，探究了VAR的文本图像编辑能力。VARIN利用一种用于argmax采样的新型伪逆函数，名为位置感知Argmax反转（Location-aware Argmax Inversion, LAI），来生成逆Gumbel噪声。这些逆噪声可实现源图像的精确重建，并促进与文本提示对齐的针对性、可控编辑。大量实验表明，VARIN能根据指定提示有效修改源图像，同时显著保留原始背景和结构细节，从而验证了其作为实用编辑方法的有效性。
英文摘要：
Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation tasks. While conditional generation has been widely explored, the ability to perform prompt-guided image editing without additional training is equally critical, as it supports numerous practical real-world applications. This paper investigates the text-to-image editing capabilities of VAR by introducing Visual AutoRegressive Inverse Noise (VARIN), the first noise inversion-based editing technique designed explicitly for VAR models. VARIN leverages a novel pseudo-inverse function for argmax sampling, named Location-aware Argmax Inversion (LAI), to generate inverse Gumbel noises. These inverse noises enable precise reconstruction of the source image and facilitate targeted, controllable edits aligned with textual prompts. Extensive experiments demonstrate that VARIN effectively modifies source images according to specified prompts while significantly preserving the original background and structural details, thus validating its efficacy as a practical editing approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
