Guided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user input (e.g., hand-drawn colored strokes) and realism of the synthesized image. Existing GAN-based methods attempt to achieve such balance using either conditional GANs or GAN inversions, which are challenging and often require additional training data or loss functions for individual applications. To address these issues, we introduce a new image synthesis and editing method, Stochastic Differential Editing (SDEdit), based on a diffusion model generative prior, which synthesizes realistic images by iteratively denoising through a stochastic differential equation (SDE). Given an input image with user guide of any type, SDEdit first adds noise to the input, then subsequently denoises the resulting image through the SDE prior to increase its realism. SDEdit does not require task-specific training or inversions and can naturally achieve the balance between realism and faithfulness. SDEdit significantly outperforms state-of-the-art GAN-based methods by up to 98.09% on realism and 91.72% on overall satisfaction scores, according to a human perception study, on multiple tasks, including stroke-based image synthesis and editing as well as image compositing.
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Institute of High Performance Computing (IHPC)（高性能计算研究所）；Centre for Frontier AI Research (CFAR)（前沿人工智能研究中心）
MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRI
Technical University of Munich（慕尼黑工业大学）；Helmholtz AI（亥姆霍兹人工智能研究所）；Helmholtz Center Munich（亥姆霍兹慕尼黑中心）；Klinikum Rechts der Isar（慕尼黑 Rechts der Isar 医院）；Kings College London（伦敦国王学院）
Text Guided Image Editing with Automatic Concept Locating and Forgetting
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Chinese Academy of Sciences（中国科学院）；Sun Yat-sen University（中山大学）；University of Auckland（奥克兰大学）；University of Missouri（密苏里大学）
提出Locate and Forget (LaF)方法，通过比较句法树自动定位图像中待修改目标概念并遗忘其存在线索，解决了文本引导图像编辑中物体属性残留问题。
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
University at Albany, State University of New York, USA（纽约州立大学奥尔巴尼分校）；Microsoft Corporation, Redmond, USA（微软公司雷德蒙德分部）；Samsung Research America AI Center, USA（三星美国研究公司人工智能中心）；University at Buffalo, State University of New York, USA（纽约州立大学布法罗分校）
East China Normal University（华东师范大学）；Xiaohongshu Inc.（小红书）；KLATASDS, MOE, China（中国教育部统计与数据科学重点实验室）；The Chinese University of Hong Kong（香港中文大学）；Zhejiang University（浙江大学）；Fudan University（复旦大学）；University of Oxford（牛津大学）；Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University（南京大学）
IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
Zhejiang University（浙江大学）；Tencent Youtu Lab（腾讯优图实验室）；Shanghai Jiao Tong University（上海交通大学）；University of Auckland（奥克兰大学）；National University of Singapore（新加坡国立大学）
JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation
Zhejiang University（浙江大学）；Tencent Youtu Lab（腾讯优图实验室）；Nanjing University（南京大学）；University of Auckland（奥克兰大学）；Fudan University（复旦大学）；National University of Singapore（新加坡国立大学）
DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing
School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）；School of Computer Science, Peking University（北京大学计算机科学学院）；Huazhong University of Science and Technology（华中科技大学）
RSEdit: Text-Guided Image Editing for Remote Sensing
School of Earth Sciences, Zhejiang University（浙江大学地球科学学院）；Zhejiang Provincial Key Laboratory of Geographic Information Science（浙江省地理信息科学重点实验室）；Key Laboratory of Spatio-temporal Information and Intelligent Services (LSIIS), Ministry of Natural Resources of the People’s Republic of China（中华人民共和国自然资源部时空信息与智能服务重点实验室）；ReLER, CCAI, Zhejiang University（ReLER，中国人工智能学会，浙江大学）
Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Meituandianping Group（美团点评集团）；Artificial Intelligence Research, CAS（中国科学院人工智能研究院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
近年来，人脸肖像编辑技术取得了很大的进步。然而，先前的方法或者1）对预定义的面部属性进行操作，缺乏控制高级语义面部组件的形状的灵活性（例如，眼睛、鼻子、嘴巴），或者2）将手动编辑的遮罩或草图作为可观察变化的中间表示，但是这样的附加输入通常需要额外的努力来获得。为了打破现有方法的局限性（例如形状、遮罩或草图），我们提出了一种新的框架r-FACE（Reference-guided FACE Component Editing），用于进行具有几何变化的多样化和可控的面组件编辑。具体而言，r-FACE以图像修补模型为主干，利用基准图像作为控制面部成分的形状的条件。为了鼓励框架集中在目标人脸组件，一个例子引导的注意力模块被设计为融合注意力特征和目标人脸组件特征提取的参考图像。通过大量的实验验证和比较，我们验证了所提出的框架的有效性。
MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion
Southeast University（东南大学）；Advanced Ocean Institute of Southeast University（东南大学先进海洋研究院）；Northwestern Polytechnical University（西北工业大学）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）；Alibaba Group（阿里巴巴集团）
