CHATEDIT：迈向基于对话的多轮交互式人脸图像编辑
CHATEDIT: Towards Multi-turn Interactive Facial Image Editing via Dialogue
AI总结：
本文提出ChatEdit基准数据集及一个集成对话与图像编辑模块的框架，用于多轮交互式人脸图像编辑，通过直接跟踪整个对话历史并修改原图，减少错误累积，实验证明其性能优于先前模型。
摘要：
本文探索了通过对话进行交互式人脸图像编辑，并引入了ChatEdit基准数据集，用于评估在此情境下的图像编辑和对话能力。ChatEdit基于CelebA-HQ数据集构建，包含了与用户在图像上的编辑请求相对应的带注释的多轮对话。该数据集具有挑战性，因为它要求系统动态跟踪用户请求、编辑图像并生成适当的响应。据此，我们提出了三个基准任务：（i）用户编辑请求跟踪，（ii）图像编辑，以及（iii）响应生成。我们提出了一个新颖的基线框架，该框架集成了用于跟踪用户请求和生成响应的对话模块，以及用于图像编辑的图像编辑模块。与以往的方法不同，我们的框架直接从截至当前轮次的整个对话历史中跟踪用户的编辑请求，并修改原始图像，而不是调整上一轮次的输出，从而减少了错误累积并防止了属性遗忘。在ChatEdit数据集上的大量实验凸显了我们的框架相对于先前模型的优越性能，同时也指出了进一步研究的潜在空间。我们将公开发布代码和数据，以促进复杂交互式人脸图像编辑的进展。
英文摘要：
This paper explores interactive facial image editing via dialogue and introduces the ChatEdit benchmark dataset for evaluating image editing and conversation abilities in this context. ChatEdit is constructed from the CelebA-HQ dataset, incorporating annotated multi-turn dialogues corresponding to user edit requests on the images. The dataset is challenging, as it requires the system to dynamically track user requests, edit images, and generate appropriate responses. Accordingly, we propose three benchmark tasks: (i) user edit request tracking, (ii) image editing, and (iii) response generation. We present a novel baseline framework that integrates a dialogue module for both tracking user requests and generating responses and an image editing module for image editing. Unlike previous approaches, our framework directly tracks user edit requests from the entire dialogue history up to the current turn and modifies the original image rather than adjusting the previous turn's output, thereby reducing error accumulation and preventing attribute forgetfulness. Extensive experiments on the ChatEdit dataset underline our framework's superior performance against prior models, while also highlighting potential room for further research. We will release the code and data publicly to facilitate advancements in complex interactive facial image editing.
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。
