LoRA of Change：学习从单张前后图像对生成用于编辑指令的LoRA
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
AI总结：
本研究提出LoC框架，通过动态学习指令专属LoRA编码前后图像对的编辑变化，结合LoRA反向优化技术仅用成对数据实现大规模训练，可支持广泛现实视觉指令的高质量图像编辑。
摘要：
本文提出了用于视觉指令图像编辑的LoRA of Change（LoC，变化LoRA）框架，其中视觉指令即前后图像对。与自然语言存在歧义、特异性不足、解读多样的问题相比，视觉指令能够准确反映用户意图。我们依托LoRA在文本驱动图像编辑与生成领域的成功应用，动态学习一个指令专属的LoRA来编码前后图像对中的“变化”，提升了模型的可解释性与可复用性。此外，通用的视觉指令图像编辑模型通常需要四元组数据，即一组前后图像对加上查询图像与目标图像。由于这类四元组数据稀缺，现有模型仅能支持范围有限的视觉指令。为突破这一限制，我们提出了LoRA反向优化技术，仅使用成对数据即可实现大规模训练。大量定性与定量实验表明，我们的模型能够生成符合用户意图的高质量图像，可支持广泛的现实世界视觉指令。
英文摘要：
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language, visual instructions can accurately reflect users' intent. Building on the success of LoRA in text-based image editing and generation, we dynamically learn an instruction-specific LoRA to encode the "change" in a before-after image pair, enhancing the interpretability and reusability of our model. Furthermore, generalizable models for image editing with visual instructions typically require quad data, i.e., a before-after image pair, along with query and target images. Due to the scarcity of such quad data, existing models are limited to a narrow range of visual instructions. To overcome this limitation, we introduce the LoRA Reverse optimization technique, enabling large-scale training with paired data alone. Extensive qualitative and quantitative experiments demonstrate that our model produces high-quality images that align with user intent and support a broad spectrum of real-world visual instructions.
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。
